View All Items

Title: LEARNING FROM GEOMETRY IN LEARNING FOR TACTICAL AND STRATEGIC DECISION DOMAINS.
Creator: Gauci, Jason, Stanley, Kenneth, University of Central Florida
Abstract / Description: Artificial neural networks (ANNs) are an abstraction of the low-level architecture of biological brains that are often applied in general problem solving and function approximation. Neuroevolution (NE), i.e. the evolution of ANNs, has proven effective at solving problems in a variety of domains. Information from the domain is input to the ANN, which outputs its desired actions. This dissertation presents a new NE algorithm called Hypercube-based NeuroEvolution of Augmenting Topologies ...
Show moreArtificial neural networks (ANNs) are an abstraction of the low-level architecture of biological brains that are often applied in general problem solving and function approximation. Neuroevolution (NE), i.e. the evolution of ANNs, has proven effective at solving problems in a variety of domains. Information from the domain is input to the ANN, which outputs its desired actions. This dissertation presents a new NE algorithm called Hypercube-based NeuroEvolution of Augmenting Topologies (HyperNEAT), based on a novel indirect encoding of ANNs. The key insight in HyperNEAT is to make the algorithm aware of the geometry in which the ANNs are embedded and thereby exploit such domain geometry to evolve ANNs more effectively. The dissertation focuses on applying HyperNEAT to tactical and strategic decision domains. These domains involve simultaneously considering short-term tactics while also balancing long-term strategies. Board games such as checkers and Go are canonical examples of such domains; however, they also include real-time strategy games and military scenarios. The dissertation details three proposed extensions to HyperNEAT designed to work in tactical and strategic decision domains. The first is an action selector ANN architecture that allows the ANN to indicate its judgements on every possible action all at once. The second technique is called substrate extrapolation. It allows learning basic concepts at a low resolution, and then increasing the resolution to learn more advanced concepts. The final extension is geometric game-tree pruning, whereby HyperNEAT can endow the ANN the ability to focus on specific areas of a domain (such as a checkers board) that deserve more inspection. The culminating contribution is to demonstrate the ability of HyperNEAT with these extensions to play Go, a most challenging game for artificial intelligence, by combining HyperNEAT with UCT.
Show less
Date Issued: 2010
Identifier: CFE0003464, ucf:48962
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0003464

Title: AUTOMATIC GRAPHICS AND GAME CONTENT GENERATION THROUGH EVOLUTIONARY COMPUTATION.
Creator: Hastings, Erin, Stanley, Kenneth, University of Central Florida
Abstract / Description: Simulation and game content includes the levels, models, textures, items, and other objects encountered and possessed by players during the game. In most modern video games and simulation software, the set of content shipped with the product is static and unchanging, or at best, randomized within a narrow set of parameters. However, ideally, if game content could be constantly and automatically renewed, players would remain engaged longer in the evolving stream of content. This dissertation...
Show moreSimulation and game content includes the levels, models, textures, items, and other objects encountered and possessed by players during the game. In most modern video games and simulation software, the set of content shipped with the product is static and unchanging, or at best, randomized within a narrow set of parameters. However, ideally, if game content could be constantly and automatically renewed, players would remain engaged longer in the evolving stream of content. This dissertation introduces three novel technologies that together realize this ambition. (1) The first, NEAT Particles, is an evolutionary method to enable users to quickly and easily create complex particle effects through a simple interactive evolutionary computation (IEC) interface. That way, particle effects become an evolvable class of content, which is exploited in the remainder of the dissertation. In particular, (2) a new algorithm called content-generating NeuroEvolution of Augmenting Topologies (cgNEAT) is introduced that automatically generates graphical and game content while the game is played, based on the past preferences of the players. Through cgNEAT, the game platform on its own can generate novel content that is designed to satisfy its players. Finally, (3) the Galactic Arms Race (GAR) multiplayer online video game is constructed to demonstrate these techniques working on a real online gaming platform. In GAR, which was made available to the public and playable online, players pilot space ships and fight enemies to acquire unique particle system weapons that are automatically evolved by the cgNEAT algorithm. The resulting study shows that cgNEAT indeed enables players to discover a wide variety of appealing content that is not only novel, but also based on and extended from previous content that they preferred in the past. The implication is that with cgNEAT it is now possible to create applications that generate their own content to satisfy users, potentially significantly reducing the cost of content creation and considerably increasing entertainment value with a constant stream of evolving content.
Show less
Date Issued: 2009
Identifier: CFE0002814, ucf:48143
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0002814

Title: MULTIAGENT LEARNING THROUGH INDIRECT ENCODING.
Creator: D'Ambrosio, David, Stanley, Kenneth, University of Central Florida
Abstract / Description: Designing a system of multiple, heterogeneous agents that cooperate to achieve a common goal is a difficult task, but it is also a common real-world problem. Multiagent learning addresses this problem by training the team to cooperate through a learning algorithm. However, most traditional approaches treat multiagent learning as a combination of multiple single-agent learning problems. This perspective leads to many inefficiencies in learning such as the problem of reinvention, whereby...
Show moreDesigning a system of multiple, heterogeneous agents that cooperate to achieve a common goal is a difficult task, but it is also a common real-world problem. Multiagent learning addresses this problem by training the team to cooperate through a learning algorithm. However, most traditional approaches treat multiagent learning as a combination of multiple single-agent learning problems. This perspective leads to many inefficiencies in learning such as the problem of reinvention, whereby fundamental skills and policies that all agents should possess must be rediscovered independently for each team member. For example, in soccer, all the players know how to pass and kick the ball, but a traditional algorithm has no way to share such vital information because it has no way to relate the policies of agents to each other.In this dissertation a new approach to multiagent learning that seeks to address these issues is presented. This approach, called multiagent HyperNEAT, represents teams as a pattern of policies rather than individual agents. The main idea is that an agent's location within a canonical team layout (such as a soccer team at the start of a game) tends to dictate its role within that team, called the policy geometry. For example, as soccer positions move from goal to center they become more offensive and less defensive, a concept that is compactly represented as a pattern. The first major contribution of this dissertation is a new method for evolving neural network controllers called HyperNEAT, which forms the foundation of the second contribution and primary focus of this work, multiagent HyperNEAT. Multiagent learning in this dissertation is investigated in predator-prey, room-clearing, and patrol domains, providing a real-world context for the approach. Interestingly, because the teams in multiagent HyperNEAT are represented as patterns they can scale up to an infinite number of multiagent policies that can be sampled from the policy geometry as needed. Thus the third contribution is a method for teams trained with multiagent HyperNEAT to dynamically scale their size without further learning. Fourth, the capabilities to both learn and scale in multiagent HyperNEAT are compared to the traditional multiagent SARSA(lamba) approach in a comprehensive study. The fifth contribution is a method for efficiently learning and encoding multiple policies for each agent on a team to facilitate learning in multi-task domains. Finally, because there is significant interest in practical applications of multiagent learning, multiagent HyperNEAT is tested in a real-world military patrolling application with actual Khepera III robots. The ultimate goal is to provide a new perspective on multiagent learning and to demonstrate the practical benefits of training heterogeneous, scalable multiagent teams through generative encoding.
Show less
Date Issued: 2011
Identifier: CFE0003661, ucf:48812
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0003661

Title: Enhancing Cognitive Algorithms for Optimal Performance of Adaptive Networks.
Creator: Lugo-Cordero, Hector, Guha, Ratan, Wu, Annie, Stanley, Kenneth, University of Central Florida
Abstract / Description: This research proposes to enhance some Evolutionary Algorithms in order to obtain optimal and adaptive network configurations. Due to the richness in technologies, low cost, and application usages, we consider Heterogeneous Wireless Mesh Networks. In particular, we evaluate the domains of Network Deployment, Smart Grids/Homes, and Intrusion Detection Systems. Having an adaptive network as one of the goals, we consider a robust noise tolerant methodology that can quickly react to changes in...
Show moreThis research proposes to enhance some Evolutionary Algorithms in order to obtain optimal and adaptive network configurations. Due to the richness in technologies, low cost, and application usages, we consider Heterogeneous Wireless Mesh Networks. In particular, we evaluate the domains of Network Deployment, Smart Grids/Homes, and Intrusion Detection Systems. Having an adaptive network as one of the goals, we consider a robust noise tolerant methodology that can quickly react to changes in the environment. Furthermore, the diversity of the performance objectives considered (e.g., power, coverage, anonymity, etc.) makes the objective function non-continuous and therefore not have a derivative. For these reasons, we enhance Particle Swarm Optimization (PSO) algorithm with elements that aid in exploring for better configurations to obtain optimal and sub-optimal configurations. According to results, the enhanced PSO promotes population diversity, leading to more unique optimal configurations for adapting to dynamic environments. The gradual complexification process demonstrated simpler optimal solutions than those obtained via trial and error without the enhancements.Configurations obtained by the modified PSO are further tuned in real-time upon environment changes. Such tuning occurs with a Fuzzy Logic Controller (FLC) which models human decision making by monitoring certain events in the algorithm. Example of such events include diversity and quality of solution in the environment. The FLC is able to adapt the enhanced PSO to changes in the environment, causing more exploration or exploitation as needed.By adding a Probabilistic Neural Network (PNN) classifier, the enhanced PSO is again used as a filter to aid in intrusion detection classification. This approach reduces miss classifications by consulting neighbors for classification in case of ambiguous samples. The performance of ambiguous votes via PSO filtering shows an improvement in classification, causing the simple classifier perform better the commonly used classifiers.
Show less
Date Issued: 2018
Identifier: CFE0007046, ucf:52003
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0007046

Title: Necessary Conditions for Open-Ended Evolution.
Creator: Soros, Lisa, Stanley, Kenneth, Gonzalez, Avelino, Wiegand, Rudolf, Cash, Mason, University of Central Florida
Abstract / Description: Evolution on Earth is widely considered to be an effectively endless process. Though this phenomenon of open-ended evolution (OEE) has been a topic of interest in the artificial life communitysince its beginnings, the field still lacks an empirically validated theory of what exactly is necessary to reproduce the phenomenon in general (including in domains quite unlike Earth). Thisdissertation (1) enumerates a set of conditions hypothesized to be necessary for OEE in addition to (2)...
Show moreEvolution on Earth is widely considered to be an effectively endless process. Though this phenomenon of open-ended evolution (OEE) has been a topic of interest in the artificial life communitysince its beginnings, the field still lacks an empirically validated theory of what exactly is necessary to reproduce the phenomenon in general (including in domains quite unlike Earth). Thisdissertation (1) enumerates a set of conditions hypothesized to be necessary for OEE in addition to (2) introducing an artificial life world called Chromaria that incorporates each of the hypothesizednecessary conditions. It then (3) describes a set of experiments with Chromaria designed to empirically validate the hypothesized necessary conditions. Thus, this dissertation describes the firstscientific endeavor to systematically test an OEE framework in an alife world and thereby make progress towards solving an open question not just for evolutionary computation and artificial life,but for science in general.
Show less
Date Issued: 2018
Identifier: CFE0007247, ucf:52205
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0007247

Title: Training Neural Networks Through the Integration of Evolution and Gradient Descent.
Creator: Morse, Gregory, Stanley, Kenneth, Wu, Annie, Shah, Mubarak, Wiegand, Rudolf, University of Central Florida
Abstract / Description: Neural networks have achieved widespread adoption due to both their applicability to a wide range of problems and their success relative to other machine learning algorithms. The training of neural networks is achieved through any of several paradigms, most prominently gradient-based approaches (including deep learning), but also through up-and-coming approaches like neuroevolution. However, while both of these neural network training paradigms have seen major improvements over the past...
Show moreNeural networks have achieved widespread adoption due to both their applicability to a wide range of problems and their success relative to other machine learning algorithms. The training of neural networks is achieved through any of several paradigms, most prominently gradient-based approaches (including deep learning), but also through up-and-coming approaches like neuroevolution. However, while both of these neural network training paradigms have seen major improvements over the past decade, little work has been invested in developing algorithms that incorporate the advances from both deep learning and neuroevolution. This dissertation introduces two new algorithms that are steps towards the integration of gradient descent and neuroevolution for training neural networks. The first is (1) the Limited Evaluation Evolutionary Algorithm (LEEA), which implements a novel form of evolution where individuals are partially evaluated, allowing rapid learning and enabling the evolutionary algorithm to behave more like gradient descent. This conception provides a critical stepping stone to future algorithms that more tightly couple evolutionary and gradient descent components. The second major algorithm (2) is Divergent Discriminative Feature Accumulation (DDFA), which combines a neuroevolution phase, where features are collected in an unsupervised manner, with a gradient descent phase for fine tuning of the neural network weights. The neuroevolution phase of DDFA utilizes an indirect encoding and novelty search, which are sophisticated neuroevolution components rarely incorporated into gradient descent-based systems. Further contributions of this work that build on DDFA include (3) an empirical analysis to identify an effective distance function for novelty search in high dimensions and (4) the extension of DDFA for the purpose of discovering convolutional features. The results of these DDFA experiments together show that DDFA discovers features that are effective as a starting point for gradient descent, with significant improvement over gradient descent alone. Additionally, the method of collecting features in an unsupervised manner allows DDFA to be applied to domains with abundant unlabeled data and relatively sparse labeled data. This ability is highlighted in the STL-10 domain, where DDFA is shown to make effective use of unlabeled data.
Show less
Date Issued: 2019
Identifier: CFE0007840, ucf:52819
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0007840

Title: A Study of Localization and Latency Reduction for Action Recognition.
Creator: Masood, Syed, Tappen, Marshall, Foroosh, Hassan, Stanley, Kenneth, Sukthankar, Rahul, University of Central Florida
Abstract / Description: The success of recognizing periodic actions in single-person-simple-background datasets, such as Weizmann and KTH, has created a need for more complex datasets to push the performance of action recognition systems. In this work, we create a new synthetic action dataset and use it to highlight weaknesses in current recognition systems. Experiments show that introducing background complexity to action video sequences causes a significant degradation in recognition performance. Moreover, this...
Show moreThe success of recognizing periodic actions in single-person-simple-background datasets, such as Weizmann and KTH, has created a need for more complex datasets to push the performance of action recognition systems. In this work, we create a new synthetic action dataset and use it to highlight weaknesses in current recognition systems. Experiments show that introducing background complexity to action video sequences causes a significant degradation in recognition performance. Moreover, this degradation cannot be fixed by fine-tuning system parameters or by selecting better feature points. Instead, we show that the problem lies in the spatio-temporal cuboid volume extracted from the interest point locations. Having identified the problem, we show how improved results can be achieved by simple modifications to the cuboids.For the above method however, one requires near-perfect localization of the action within a video sequence. To achieve this objective, we present a two stage weakly supervised probabilistic model for simultaneous localization and recognition of actions in videos. Different from previous approaches, our method is novel in that it (1) eliminates the need for manual annotations for the training procedure and (2) does not require any human detection or tracking in the classification stage. The first stage of our framework is a probabilistic action localization model which extracts the most promising sub-windows in a video sequence where an action can take place. We use a non-linear classifier in the second stage of our framework for the final classification task. We show the effectiveness of our proposed model on two well known real-world datasets: UCF Sports and UCF11 datasets.Another application of the weakly supervised probablistic model proposed above is in the gaming environment. An important aspect in designing interactive, action-based interfaces is reliably recognizing actions with minimal latency. High latency causes the system's feedback to lag behind and thus significantly degrade the interactivity of the user experience. With slight modification to the weakly supervised probablistic model we proposed for action localization, we show how it can be used for reducing latency when recognizing actions in Human Computer Interaction (HCI) environments. This latency-aware learning formulation trains a logistic regression-based classifier that automatically determines distinctive canonical poses from the data and uses these to robustly recognize actions in the presence of ambiguous poses. We introduce a novel (publicly released) dataset for the purpose of our experiments. Comparisons of our method against both a Bag of Words and a Conditional Random Field (CRF) classifier show improved recognition performance for both pre-segmented and online classification tasks.
Show less
Date Issued: 2012
Identifier: CFE0004575, ucf:49210
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0004575

Title: Effective Task Transfer Through Indirect Encoding.
Creator: Verbancsics, Phillip, Stanley, Kenneth, Sukthankar, Gita, Georgiopoulos, Michael, Garibay, Ivan, University of Central Florida
Abstract / Description: An important goal for machine learning is to transfer knowledge between tasks. For example, learning to play RoboCup Keepaway should contribute to learning the full game of RoboCup soccer. Often approaches to task transfer focus on transforming the original representation to fit the new task. Such representational transformations are necessary because the target task often requires new state information that was not included in the original representation. In RoboCup Keepaway, changing from...
Show moreAn important goal for machine learning is to transfer knowledge between tasks. For example, learning to play RoboCup Keepaway should contribute to learning the full game of RoboCup soccer. Often approaches to task transfer focus on transforming the original representation to fit the new task. Such representational transformations are necessary because the target task often requires new state information that was not included in the original representation. In RoboCup Keepaway, changing from the 3 vs. 2 variant of the task to 4 vs. 3 adds state information for each of the new players. In contrast, this dissertation explores the idea that transfer is most effective if the representation is designed to be the same even across different tasks. To this end, (1) the bird's eye view (BEV) representation is introduced, which can represent different tasks on the same two-dimensional map. Because the BEV represents state information associated with positions instead of objects, it can be scaled to more objects without manipulation. In this way, both the 3 vs. 2 and 4 vs. 3 Keepaway tasks can be represented on the same BEV, which is (2) demonstrated in this dissertation.Yet a challenge for such representation is that a raw two-dimensional map is high-dimensional and unstructured. This dissertation demonstrates how this problem is addressed naturally by the Hypercube-based NeuroEvolution of Augmenting Topologies (HyperNEAT) approach. HyperNEAT evolves an indirect encoding, which compresses the representation by exploiting its geometry. The dissertation then explores further exploiting the power of such encoding, beginning by (3) enhancing the configuration of the BEV with a focus on modularity. The need for further nonlinearity is then (4) investigated through the addition of hidden nodes. Furthermore, (5) the size of the BEV can be manipulated because it is indirectly encoded. Thus the resolution of the BEV, which is dictated by its size, is increased in precision and culminates in a HyperNEAT extension that is expressed at effectively infinite resolution. Additionally, scaling to higher resolutions through gradually increasing the size of the BEV is explored. Finally, (6) the ambitious problem of scaling from the Keepaway task to the Half-field Offense task is investigated with the BEV. Overall, this dissertation demonstrates that advanced representations in conjunction with indirect encoding can contribute to scaling learning techniques to more challenging tasks, such as the Half-field Offense RoboCup soccer domain.
Show less
Date Issued: 2011
Identifier: CFE0004174, ucf:49071
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0004174

Title: Evolution Through the Search for Novelty.
Creator: Lehman, Joel, Stanley, Kenneth, Gonzalez, Avelino, Wiegand, Rudolf, Hoffman, Eric, University of Central Florida
Abstract / Description: I present a new approach to evolutionary search called novelty search, wherein only behavioral novelty is rewarded, thereby abstracting evolution as a search for novel forms. This new approach contrasts with the traditional approach of rewarding progress towards the objective through an objective function. Although they are designed to light a path to the objective, objective functions can instead deceive search into converging to dead ends called local optima.As a significant problem in...
Show moreI present a new approach to evolutionary search called novelty search, wherein only behavioral novelty is rewarded, thereby abstracting evolution as a search for novel forms. This new approach contrasts with the traditional approach of rewarding progress towards the objective through an objective function. Although they are designed to light a path to the objective, objective functions can instead deceive search into converging to dead ends called local optima.As a significant problem in evolutionary computation, deception has inspired many techniques designed to mitigate it. However, nearly all such methods are still ultimately susceptible to deceptive local optima because they still measure progress with respect to the objective, which this dissertation will show is often a broken compass. Furthermore, although novelty search completely abandons the objective, it counterintuitively often outperforms methods that search directly for the objective in deceptive tasks and can induce evolutionary dynamics closer in spirit to natural evolution. The main contributions are to (1) introduce novelty search, an example of an effective search method that is not guided by actively measuring or encouraging objective progress; (2) validate novelty search by applying it to biped locomotion; (3) demonstrate novelty search's benefits for evolvability (i.e. the abilityof an organism to further evolve) in a variety of domains; (4) introduce an extension of novelty search called minimal criteria novelty search that brings a new abstraction of natural evolution to evolutionary computation (i.e. evolution as a search for many ways of meeting the minimal criteria of life); (5) present a second extension of novelty search called novelty search with local competition that abstracts evolution instead as a process driven towards diversity with competition playing a subservient role; and (6) evolve a diversity of functional virtual creatures in a single run as a culminating application of novelty search with local competition. Overall these contributions establish novelty search as an important new research direction for the field of evolutionary computation.
Show less
Date Issued: 2012
Identifier: CFE0004398, ucf:49390
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0004398

Title: Towards Evolving More Brain-Like Artificial Neural Networks.
Creator: Risi, Sebastian, Stanley, Kenneth, Hughes, Charles, Sukthankar, Gita, Wiegand, Rudolf, University of Central Florida
Abstract / Description: An ambitious long-term goal for neuroevolution, which studies how artificial evolutionary processes can be driven to produce brain-like structures, is to evolve neurocontrollers with a high density of neurons and connections that can adapt and learn from past experience. Yet while neuroevolution has produced successful results in a variety of domains, the scale of natural brains remains far beyond reach. In this dissertation two extensions to the recently introduced Hypercube-based...
Show moreAn ambitious long-term goal for neuroevolution, which studies how artificial evolutionary processes can be driven to produce brain-like structures, is to evolve neurocontrollers with a high density of neurons and connections that can adapt and learn from past experience. Yet while neuroevolution has produced successful results in a variety of domains, the scale of natural brains remains far beyond reach. In this dissertation two extensions to the recently introduced Hypercube-based NeuroEvolution of Augmenting Topologies (HyperNEAT) approach are presented that are a step towards more brain-like artificial neural networks (ANNs). First, HyperNEAT is extended to evolve plastic ANNs that can learn from past experience. This new approach, called adaptive HyperNEAT, allows not only patterns of weights across the connectivity of an ANN to be generated by a function of its geometry, but also patterns of arbitrary local learning rules. Second, evolvable-substrate HyperNEAT (ES-HyperNEAT) is introduced, which relieves the user from deciding where the hidden nodes should be placed in a geometry that is potentially infinitely dense. This approach not only can evolve the location of every neuron in the network, but also can represent regions of varying density, which means resolution can increase holistically over evolution. The combined approach, adaptive ES-HyperNEAT, unifies for the first time in neuroevolution the abilities to indirectly encode connectivity through geometry, generate patterns of heterogeneous plasticity, and simultaneously encode the density and placement of nodes in space. The dissertation culminates in a major application domain that takes a step towards the general goal of adaptive neurocontrollers for legged locomotion.
Show less
Date Issued: 2012
Identifier: CFE0004287, ucf:49477
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0004287

Title: Quality Diversity: Harnessing Evolution to Generate a Diversity of High-Performing Solutions.
Creator: Pugh, Justin, Stanley, Kenneth, Wu, Annie, Sukthankar, Gita, Garibay, Ivan, University of Central Florida
Abstract / Description: Evolution in nature has designed countless solutions to innumerable interconnected problems, giving birth to the impressive array of complex modern life observed today. Inspired by this success, the practice of evolutionary computation (EC) abstracts evolution artificially as a search operator to find solutions to problems of interest primarily through the adaptive mechanism of survival of the fittest, where stronger candidates are pursued at the expense of weaker ones until a solution of...
Show moreEvolution in nature has designed countless solutions to innumerable interconnected problems, giving birth to the impressive array of complex modern life observed today. Inspired by this success, the practice of evolutionary computation (EC) abstracts evolution artificially as a search operator to find solutions to problems of interest primarily through the adaptive mechanism of survival of the fittest, where stronger candidates are pursued at the expense of weaker ones until a solution of satisfying quality emerges. At the same time, research in open-ended evolution (OEE) draws different lessons from nature, seeking to identify and recreate processes that lead to the type of perpetual innovation and indefinitely increasing complexity observed in natural evolution. New algorithms in EC such as MAP-Elites and Novelty Search with Local Competition harness the toolkit of evolution for a related purpose: finding as many types of good solutions as possible (rather than merely the single best solution). With the field in its infancy, no empirical studies previously existed comparing these so-called quality diversity (QD) algorithms. This dissertation (1) contains the first extensive and methodical effort to compare different approaches to QD (including both existing published approaches as well as some new methods presented for the first time here) and to understand how they operate to help inform better approaches in the future.It also (2) introduces a new technique for encoding neural networks for evolution with indirect encoding that contain multiple sensory or output modalities.Further, it (3) explores the idea that QD can act as an engine of open-ended discovery by introducing an expressive platform called Voxelbuild where QD algorithms continually evolve robots that stack blocks in new ways. A culminating experiment (4) is presented that investigates evolution in Voxelbuild over a very long timescale. This research thus stands to advance the OEE community's desire to create and understand open-ended systems while also laying the groundwork for QD to realize its potential within EC as a means to automatically generate an endless progression of new content in real-world applications.
Show less
Date Issued: 2019
Identifier: CFE0007513, ucf:52638
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0007513

Title: Detecting, Tracking, and Recognizing Activities in Aerial Video.
Creator: Reilly, Vladimir, Shah, Mubarak, Georgiopoulos, Michael, Stanley, Kenneth, Dogariu, Aristide, University of Central Florida
Abstract / Description: In this dissertation we address the problem of detecting humans and vehicles, tracking their identities in crowded scenes, and finally determining human activities. First, we tackle the problem of detecting moving as well as stationary objects in scenes that contain parallax and shadows. We constrain the search of pedestrians and vehicles by representing them as shadow casting out of plane or (SCOOP) objects.Next, we propose a novel method for tracking a large number of densely moving objects...
Show moreIn this dissertation we address the problem of detecting humans and vehicles, tracking their identities in crowded scenes, and finally determining human activities. First, we tackle the problem of detecting moving as well as stationary objects in scenes that contain parallax and shadows. We constrain the search of pedestrians and vehicles by representing them as shadow casting out of plane or (SCOOP) objects.Next, we propose a novel method for tracking a large number of densely moving objects in aerial video. We divide the scene into grid cells to define a set of local scene constraints which we use as part of the matching cost function to solve the tracking problem which allows us to track fast-moving objects in low frame rate videos.Finally, we propose a method for recognizing human actions from few examples. We use the bag of words action representation, assume that most of the classes have many examples, and construct Support Vector Machine models for each class. We then use Support Vector Machines for classes with many examples to improve the decision function of the Support Vector Machine that was trained using few examples via late fusion of weighted decision values.
Show less
Date Issued: 2012
Identifier: CFE0004627, ucf:49935
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0004627

Title: Dictionary Learning for Image Analysis.
Creator: Khan, Muhammad Nazar, Tappen, Marshall, Foroosh, Hassan, Stanley, Kenneth, Li, Xin, University of Central Florida
Abstract / Description: In this thesis, we investigate the use of dictionary learning for discriminative tasks on natural images. Our contributions can be summarized as follows:1) We introduce discriminative deviation based learning to achieve principled handling of the reconstruction-discrimination tradeoff that is inherent to discriminative dictionary learning.2) Since natural images obey a strong smoothness prior, we show how spatial smoothness constraints can be incorporated into the learning formulation by...
Show moreIn this thesis, we investigate the use of dictionary learning for discriminative tasks on natural images. Our contributions can be summarized as follows:1) We introduce discriminative deviation based learning to achieve principled handling of the reconstruction-discrimination tradeoff that is inherent to discriminative dictionary learning.2) Since natural images obey a strong smoothness prior, we show how spatial smoothness constraints can be incorporated into the learning formulation by embedding dictionary learning into Conditional Random Field (CRF) learning. We demonstrate that such smoothness constraints can lead to state-of-the-art performance for pixel-classification tasks.3) Finally, we lay down the foundations of super-latent learning. By treating sparse codes on a CRF as latent variables, dictionary learning can also be performed via the Latent (Structural) SVM formulation for jointly learning a classifier over the sparse codes. The dictionary is treated as a super-latent variable that generates the latent variables.
Show less
Date Issued: 2013
Identifier: CFE0004701, ucf:49844
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0004701

Title: A Fitness Function Elimination Theory for Blackbox Optimization and Problem Class Learning.
Creator: Anil, Gautham, Wu, Annie, Wiegand, Rudolf, Stanley, Kenneth, Clarke, Thomas, Jansen, Thomas, University of Central Florida
Abstract / Description: The modern view of optimization is that optimization algorithms are not designed in a vacuum, but can make use of information regarding the broad class of objective functions from which a problem instance is drawn. Using this knowledge, we want to design optimization algorithms that execute quickly (efficiency), solve the objective function with minimal samples (performance), and are applicable over a wide range of problems (abstraction). However, we present a new theory for blackbox...
Show moreThe modern view of optimization is that optimization algorithms are not designed in a vacuum, but can make use of information regarding the broad class of objective functions from which a problem instance is drawn. Using this knowledge, we want to design optimization algorithms that execute quickly (efficiency), solve the objective function with minimal samples (performance), and are applicable over a wide range of problems (abstraction). However, we present a new theory for blackbox optimization from which, we conclude that of these three desired characteristics, only two can be maximized by any algorithm.We put forward an alternate view of optimization where we use knowledge about the problem class and samples from the problem instance to identify which problem instances from the class are being solved. From this Elimination of Fitness Functions approach, an idealized optimization algorithm that minimizes sample counts over any problem class, given complete knowledge about the class, is designed. This theory allows us to learn more about the difficulty of various problems, and we are able to use it to develop problem complexity bounds.We present general methods to model this algorithm over a particular problem class and gain efficiency at the cost of specifically targeting that class. This is demonstrated over the Generalized Leading-Ones problem and a generalization called LO**, and efficient algorithms with optimal performance are derived and analyzed. We also tighten existing bounds for LO***. Additionally, we present a probabilistic framework based on our Elimination of Fitness Functions approach that clarifies how one can ideally learn about the problem class we face from the objective functions. This problem learning increases the performance of an optimization algorithm at the cost of abstraction.In the context of this theory, we re-examine the blackbox framework as an algorithm design framework and suggest several improvements to existing methods, including incorporating problem learning, not being restricted to blackbox framework and building parametrized algorithms. We feel that this theory and our recommendations will help a practitioner make substantially better use of all that is available in typical practical optimization algorithm design scenarios.
Show less
Date Issued: 2012
Identifier: CFE0004511, ucf:49268
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0004511

Title: Novelty-Assisted Interactive Evolution of Control Behaviors.
Creator: Woolley, Brian, Stanley, Kenneth, Hughes, Charles, Gonzalez, Avelino, Wu, Annie, Hancock, Peter, University of Central Florida
Abstract / Description: The field of evolutionary computation is inspired by the achievements of natural evolution, in which there is no final objective. Yet the pursuit of objectives is ubiquitous in simulated evolution because evolutionary algorithms that can consistently achieve established benchmarks are lauded as successful, thus reinforcing this paradigm. A significant problem is that such objective approaches assume that intermediate stepping stones will increasingly resemble the final objective when in fact...
Show moreThe field of evolutionary computation is inspired by the achievements of natural evolution, in which there is no final objective. Yet the pursuit of objectives is ubiquitous in simulated evolution because evolutionary algorithms that can consistently achieve established benchmarks are lauded as successful, thus reinforcing this paradigm. A significant problem is that such objective approaches assume that intermediate stepping stones will increasingly resemble the final objective when in fact they often do not. The consequence is that while solutions may exist, searching for such objectives may not discover them. This problem with objectives is demonstrated through an experiment in this dissertation that compares how images discovered serendipitously during interactive evolution in an online system called Picbreeder cannot be rediscovered when they become the final objective of the very same algorithm that originally evolved them. This negative result demonstrates that pursuing an objective limits evolution by selecting offspring only based on the final objective. Furthermore, even when high fitness is achieved, the experimental results suggest that the resulting solutions are typically brittle, piecewise representations that only perform well by exploiting idiosyncratic features in the target. In response to this problem, the dissertation next highlights the importance of leveraging human insight during search as an alternative to articulating explicit objectives. In particular, a new approach called novelty-assisted interactive evolutionary computation (NA-IEC) combines human intuition with a method called novelty search for the first time to facilitate the serendipitous discovery of agent behaviors. In this approach, the human user directs evolution by selecting what is interesting from the on-screen population of behaviors. However, unlike in typical IEC, the user can then request that the next generation be filled with novel descendants, as opposed to only the direct descendants of typical IEC. The result of such an approach, unconstrained by a priori objectives, is that it traverses key stepping stones that ultimately accumulate meaningful domain knowledge.To establishes this new evolutionary approach based on the serendipitous discovery of key stepping stones during evolution, this dissertation consists of four key contributions: (1) The first contribution establishes the deleterious effects of a priori objectives on evolution. The second (2) introduces the NA-IEC approach as an alternative to traditional objective-based approaches. The third (3) is a proof-of-concept that demonstrates how combining human insight with novelty search finds solutions significantly faster and at lower genomic complexities than fully-automated processes, including pure novelty search, suggesting an important role for human users in the search for solutions. Finally, (4) the NA-IEC approach is applied in a challenge domain wherein leveraging human intuition and domain knowledge accelerates the evolution of solutions for the nontrivial octopus-arm control task. The culmination of these contributions demonstrates the importance of incorporating human insights into simulated evolution as a means to discovering better solutions more rapidly than traditional approaches.
Show less
Date Issued: 2012
Identifier: CFE0004462, ucf:49335
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0004462

Title: Learning Hierarchical Representations for Video Analysis Using Deep Learning.
Creator: Yang, Yang, Shah, Mubarak, Sukthankar, Gita, Da Vitoria Lobo, Niels, Stanley, Kenneth, Sukthankar, Rahul, University of Central Florida
Abstract / Description: With the exponential growth of the digital data, video content analysis (e.g., action, event recognition) has been drawing increasing attention from computer vision researchers. Effective modeling of the objects, scenes, and motions is critical for visual understanding. Recently there has been a growing interest in the bio-inspired deep learning models, which has shown impressive results in speech and object recognition. The deep learning models are formed by the composition of multiple non...
Show moreWith the exponential growth of the digital data, video content analysis (e.g., action, event recognition) has been drawing increasing attention from computer vision researchers. Effective modeling of the objects, scenes, and motions is critical for visual understanding. Recently there has been a growing interest in the bio-inspired deep learning models, which has shown impressive results in speech and object recognition. The deep learning models are formed by the composition of multiple non-linear transformations of the data, with the goal of yielding more abstract and ultimately more useful representations. The advantages of the deep models are three fold: 1) They learn the features directly from the raw signal in contrast to the hand-designed features. 2) The learning can be unsupervised, which is suitable for large data where labeling all the data is expensive and unpractical. 3) They learn a hierarchy of features one level at a time and the layerwise stacking of feature extraction, this often yields better representations.However, not many deep learning models have been proposed to solve the problems in video analysis, especially videos ``in a wild''. Most of them are either dealing with simple datasets, or limited to the low-level local spatial-temporal feature descriptors for action recognition. Moreover, as the learning algorithms are unsupervised, the learned features preserve generative properties rather than the discriminative ones which are more favorable in the classification tasks. In this context, the thesis makes two major contributions.First, we propose several formulations and extensions of deep learning methods which learn hierarchical representations for three challenging video analysis tasks, including complex event recognition, object detection in videos and measuring action similarity. The proposed methods are extensively demonstrated for each work on the state-of-the-art challenging datasets. Besides learning the low-level local features, higher level representations are further designed to be learned in the context of applications. The data-driven concept representations and sparse representation of the events are learned for complex event recognition; the representations for object body parts and structures are learned for object detection in videos; and the relational motion features and similarity metrics between video pairs are learned simultaneously for action verification.Second, in order to learn discriminative and compact features, we propose a new feature learning method using a deep neural network based on auto encoders. It differs from the existing unsupervised feature learning methods in two ways: first it optimizes both discriminative and generative properties of the features simultaneously, which gives our features a better discriminative ability. Second, our learned features are more compact, while the unsupervised feature learning methods usually learn a redundant set of over-complete features. Extensive experiments with quantitative and qualitative results on the tasks of human detection and action verification demonstrate the superiority of our proposed models.
Show less
Date Issued: 2013
Identifier: CFE0004964, ucf:49593
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0004964

Title: Pervasive Secure Content Delivery Networks Implementation.
Creator: Lugo-Cordero, Hector, Guha, Ratan, Stanley, Kenneth, Chatterjee, Mainak, Wu, Annie, Lu, Kejie, University of Central Florida
Abstract / Description: Over the years, communication networks have been shifting their focus from providing connectivity in a client/server model to providing a service or content. This shift has led to topic areas like Service-Oriented Architecture (SOA), Heterogeneous Wireless Mesh Networks, and Ubiquitous Computing. Furthermore, probably the broadest of these areas which embarks all is the Internet of Things (IoT). The IoT is defined as an Internet where all physical entities (e.g., vehicles, appliances, smart...
Show moreOver the years, communication networks have been shifting their focus from providing connectivity in a client/server model to providing a service or content. This shift has led to topic areas like Service-Oriented Architecture (SOA), Heterogeneous Wireless Mesh Networks, and Ubiquitous Computing. Furthermore, probably the broadest of these areas which embarks all is the Internet of Things (IoT). The IoT is defined as an Internet where all physical entities (e.g., vehicles, appliances, smart phones, smart homes, computers, etc.), which we interact daily are connected and exchanging data among themselves and users. The IoT has become a global goal for companies, researchers, and users alike due to its different implementation and functional benefits: performance efficiency, coverage, economic and health. Due to the variety of devices which connect to it, it is expected that the IoT is composed of multiple technologies interacting together, to deliver a service. This technologies interactions renders an important challenge that must be overcome: how to communicate these technologies effectively and securely? The answer to this question is vital for a successful deployment of IoT and achievement of all the potential benefits that the IoT promises.This thesis proposes a SOA approach at the Network Layer to be able to integrate all technologies involved, in a transparent manner. The proposed set of solutions is composed of primarily the secure implementation of a unifying routing algorithm and a layered messaging model to standardizecommunication of all devices. Security is targeted to address the three main security concerns (i.e., confidentiality, integrity, and availability), with pervasive schemes that can be employed for any kind of device on the client, backbone, and server side. The implementation of such schemes is achieved by standard current security mechanisms (e.g., encryption), in combination with novel context and intelligent checks that detect compromised devices. Moreover, a decentralized content processing design is presented. In such design, content processing is handled at the client side, allowing server machines to serve more content, while being more reliable and capable of processing complete security checks on data and client integrity.
Show less
Date Issued: 2017
Identifier: CFE0006620, ucf:51268
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0006620

Title: Worldwide Infrastructure for Neuroevolution: A Modular Library to Turn Any Evolutionary Domain into an Online Interactive Platform.
Creator: Szerlip, Paul, Stanley, Kenneth, Laviola II, Joseph, Wu, Annie, Kim, Joo, University of Central Florida
Abstract / Description: Across many scientific disciplines, there has emerged an open opportunity to utilize the scale and reach of the Internet to collect scientific contributions from scientists and non-scientists alike. This process, called citizen science, has already shown great promise in the fields of biology and astronomy. Within the fields of artificial life (ALife) and evolutionary computation (EC) experiments in collaborative interactive evolution (CIE) have demonstrated the ability to collect thousands...
Show moreAcross many scientific disciplines, there has emerged an open opportunity to utilize the scale and reach of the Internet to collect scientific contributions from scientists and non-scientists alike. This process, called citizen science, has already shown great promise in the fields of biology and astronomy. Within the fields of artificial life (ALife) and evolutionary computation (EC) experiments in collaborative interactive evolution (CIE) have demonstrated the ability to collect thousands of experimental contributions from hundreds of users across the glob. However, such collaborative evolutionary systems can take nearly a year to build with a small team of researchers. This dissertation introduces a new developer framework enabling researchers to easily build fully persistent online collaborative experiments around almost any evolutionary domain, thereby reducing the time to create such systems to weeks for a single researcher. To add collaborative functionality to any potential domain, this framework, called Worldwide Infrastructure for Neuroevolution (WIN), exploits an important unifying principle among all evolutionary algorithms: regardless of the overall methods and parameters of the evolutionary experiment, every individual created has an explicit parent-child relationship, wherein one individual is considered the direct descendant of another. This principle alone is enough to capture and preserve the relationships and results for a wide variety of evolutionary experiments, while allowing multiple human users to meaningfully contribute. The WIN framework is first validated through two experimental domains, image evolution and a new two-dimensional virtual creature domain, Indirectly Encoded SodaRace (IESoR), that is shown to produce a visually diverse variety of ambulatory creatures. Finally, an Android application built with WIN, #filters, allows users to interactively evolve custom image effects to apply to personalized photographs, thereby introducing the first CIE application available for any mobile device. Together, these collaborative experiments and new mobile application establish a comprehensive new platform for evolutionary computation that can change how researchers design and conduct citizen science online.
Show less
Date Issued: 2015
Identifier: CFE0005889, ucf:50892
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0005889

Title: Batch and Online Implicit Weighted Gaussian Processes for Robust Novelty Detection.
Creator: Ramirez Padron, Ruben, Gonzalez, Avelino, Georgiopoulos, Michael, Stanley, Kenneth, Mederos, Boris, Wang, Chung-Ching, University of Central Florida
Abstract / Description: This dissertation aims mainly at obtaining robust variants of Gaussian processes (GPs) that do not require using non-Gaussian likelihoods to compensate for outliers in the training data. Bayesian kernel methods, and in particular GPs, have been used to solve a variety of machine learning problems, equating or exceeding the performance of other successful techniques. That is the case of a recently proposed approach to GP-based novelty detection that uses standard GPs (i.e. GPs employing...
Show moreThis dissertation aims mainly at obtaining robust variants of Gaussian processes (GPs) that do not require using non-Gaussian likelihoods to compensate for outliers in the training data. Bayesian kernel methods, and in particular GPs, have been used to solve a variety of machine learning problems, equating or exceeding the performance of other successful techniques. That is the case of a recently proposed approach to GP-based novelty detection that uses standard GPs (i.e. GPs employing Gaussian likelihoods). However, standard GPs are sensitive to outliers in training data, and this limitation carries over to GP-based novelty detection. This limitation has been typically addressed by using robust non-Gaussian likelihoods. However, non-Gaussian likelihoods lead to analytically intractable inferences, which require using approximation techniques that are typically complex and computationally expensive. Inspired by the use of weights in quasi-robust statistics, this work introduces a particular type of weight functions, called here data weighers, in order to obtain robust GPs that do not require approximation techniques and retain the simplicity of standard GPs. This work proposes implicit weighted variants of batch GP, online GP, and sparse online GP (SOGP) that employ weighted Gaussian likelihoods. Mathematical expressions for calculating the posterior implicit weighted GPs are derived in this work. In our experiments, novelty detection based on our weighted batch GPs consistently and significantly outperformed standard batch GP-based novelty detection whenever data was contaminated with outliers. Additionally, our experiments show that novelty detection based on online GPs can perform similarly to batch GP-based novelty detection. Membership scores previously introduced by other authors are also compared in our experiments.
Show less
Date Issued: 2015
Identifier: CFE0005869, ucf:50858
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0005869

Title: Computational Methods for Comparative Non-coding RNA Analysis: from Secondary Structures to Tertiary Structures.
Creator: Ge, Ping, Zhang, Shaojie, Guha, Ratan, Stanley, Kenneth, Jha, Sumit, Song, Hojun, University of Central Florida
Abstract / Description: Unlike message RNAs (mRNAs) whose information is encoded in the primary sequences, the cellular roles of non-coding RNAs (ncRNAs) originate from the structures. Therefore studying the structural conservation in ncRNAs is important to yield an in-depth understanding of their functionalities. In the past years, many computational methods have been proposed to analyze the common structural patterns in ncRNAs using comparative methods. However, the RNA structural comparison is not a trivial task,...
Show moreUnlike message RNAs (mRNAs) whose information is encoded in the primary sequences, the cellular roles of non-coding RNAs (ncRNAs) originate from the structures. Therefore studying the structural conservation in ncRNAs is important to yield an in-depth understanding of their functionalities. In the past years, many computational methods have been proposed to analyze the common structural patterns in ncRNAs using comparative methods. However, the RNA structural comparison is not a trivial task, and the existing approaches still have numerous issues in efficiency and accuracy. In this dissertation, we will introduce a suite ofnovel computational tools that extend the classic models for ncRNA secondary and tertiary structure comparisons.For RNA secondary structure analysis, we first developed a computational tool, named PhyloRNAalifold, to integrate the phylogenetic information into the consensus structural folding. The underlying idea of this algorithm is that the importance of a co-varying mutation should be determined by its position on the phylogenetic tree. By assigning high scores to the critical covariances, the prediction of RNA secondary structure can be more accurate. Besides structure prediction, we also developed a computational tool, named ProbeAlign, to improvethe efficiency of genome-wide ncRNA screening by using high-throughput RNA structural probing data. It treats the chemical reactivities embedded in the probing information as pairing attributes of the searching targets. This approach can avoid the time-consuming base pair matching in the secondary structure alignment. The application of ProbeAlign to the FragSeq datasets shows its capability of genome-wide ncRNAs analysis.For RNA tertiary structure analysis, we first developed a computational tool, named STAR3D, to find the global conservation in RNA 3D structures. STAR3D aims at finding the consensus of stacks by using 2D topology and 3D geometry together. Then, the loop regions can be ordered and aligned according to their relative positions in the consensus. This stack-guided alignment method adopts the divide-and-conquer strategy into RNA 3D structural alignment, which has improved its efficiency dramatically. Furthermore, we also have clustered all loop regions in non-redundant RNA 3D structures to de novo detect plausible RNA structural motifs. The computational pipeline, named RNAMSC, was extended to handle large-scale PDB datasets, and solid downstream analysis was performed to ensure the clustering results are valid and easily to be applied to further research. The final results contain many interesting variations of known motifs, such as GNAA tetraloop, kink-turn, sarcin-ricin and t-loops. We also discovered novel functional motifs that conserved in a wide range of ncRNAs, including ribosomal RNA, sgRNA, SRP RNA, GlmS riboswitch and twister ribozyme.
Show less
Date Issued: 2016
Identifier: CFE0006104, ucf:51212
Format: Document (PDF)
PURL: http://purl.flvc.org/ucf/fd/CFE0006104

NEAT (5)	+ -
HyperNEAT (4)	+ -
neuroevolution (4)	+ -
Neuroevolution (3)	+ -
neural networks (3)	+ -

open-ended evolution (3)	+ -
Interactive Evolutionary Computation (2)	+ -
Machine Learning (2)	+ -
NeuroEvolution of Augmenting Topologies (2)	+ -
artificial life (2)	+ -
evolutionary computation (2)	+ -
machine learning (2)	+ -
novelty search (2)	+ -
quality diversity (2)	+ -
tracking (2)	+ -
Action Recognition (1)	+ -
Active Set Method (1)	+ -
Activity Recognition (1)	+ -
Approximate Kernel Path (1)	+ -
Approximate Regularization Path (1)	+ -
Artificial Evolution (1)	+ -
Artificial Intelligence (1)	+ -
Artificial Neural Networks (1)	+ -
Atmospheric Turbulence (1)	+ -
Augmented Lagrange Multiplier (1)	+ -
Background Subtraction (1)	+ -
Bayesian machine learning (1)	+ -
Blackbox Complexity (1)	+ -
Camera Motion Estimation (1)	+ -
Comparative method (1)	+ -

Stanley, Kenneth (24)	+ -
University of Central Florida (24)	+ -
Wu, Annie (8)	+ -
Shah, Mubarak (5)	+ -
Wiegand, Rudolf (5)	+ -

Georgiopoulos, Michael (4)	+ -
Gonzalez, Avelino (4)	+ -
Sukthankar, Gita (4)	+ -
Da Vitoria Lobo, Niels (3)	+ -
Guha, Ratan (3)	+ -
Foroosh, Hassan (2)	+ -
Garibay, Ivan (2)	+ -
Hughes, Charles (2)	+ -
Laviola II, Joseph (2)	+ -
Li, Xin (2)	+ -
Lugo-Cordero, Hector (2)	+ -
Sukthankar, Rahul (2)	+ -
Tappen, Marshall (2)	+ -
Anagnostopoulos, Georgios (1)	+ -
Anderson, Thaddeus (1)	+ -
Anil, Gautham (1)	+ -
Atia, George (1)	+ -
Cash, Mason (1)	+ -
Chatterjee, Mainak (1)	+ -
Clarke, Thomas (1)	+ -
D'Ambrosio, David (1)	+ -
Dogariu, Aristide (1)	+ -
Gauci, Jason (1)	+ -
Ge, Ping (1)	+ -
Hancock, Peter (1)	+ -

Search In

Pages

Pages

Sort Results By:

Narrow results by:

Topical Subject

Collection

Type of Resource

Language

Creator

Format

Owner