View All Items

Title: The human face recognition problem: A solution based on third-order synthetic neural networks and isodensity analysis.
Creator: Uwechue, Okechukwu A., Florida Atlantic University, Pandya, Abhijit S., College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
Abstract/Description: Third-order synthetic neural networks are applied to the recognition of isodensity facial images extracted from digitized grayscale facial images. A key property of neural networks is their ability to recognize invariances and extract essential parameters from complex high-dimensional data. In pattern recognition an input image must be recognized regardless of its position, size, and angular orientation. In order to achieve this, the neural network needs to learn the relationships between the...
Show moreThird-order synthetic neural networks are applied to the recognition of isodensity facial images extracted from digitized grayscale facial images. A key property of neural networks is their ability to recognize invariances and extract essential parameters from complex high-dimensional data. In pattern recognition an input image must be recognized regardless of its position, size, and angular orientation. In order to achieve this, the neural network needs to learn the relationships between the input pixels. Pattern recognition requires the nonlinear subdivision of the pattern space into subsets representing the objects to be identified. Single-layer neural networks can only perform linear discrimination. However, multilayer first-order networks and high-order neural networks can both achieve this. The most significant advantage of a higher-order net over a traditional multilayer perceptron is that invariances to 2-dimensional geometric transformations can be incorporated into the network and need not be learned through prolonged training with an extensive family of exemplars. It is shown that a third-order network can be used to achieve translation-, scale-, and rotation-invariant recognition with a significant reduction in training time over other neural net paradigms such as the multilayer perceptron. A model based on an enhanced version of the Widrow-Hoff training algorithm and a new momentum paradigm are introduced and applied to the complex problem of human face recognition under varying facial expressions. Arguments for the use of isodensity information in the recognition algorithm are put forth and it is shown how the technique of coarse-coding is applied to reduce the memory required for computer simulations. The combination of isodensity information and neural networks for image recognition is described and its merits over other image recognition methods are explained. It is shown that isodensity information coupled with the use of an "adaptive threshold strategy" (ATS) yields a system that is relatively impervious to image contrast noise. The new momentum paradigm produces much faster convergence rates than ordinary momentum and renders the network behaviour independent of its training parameters over a broad range of parameter values.
Show less
Date Issued: 1996
PURL: http://purl.flvc.org/fcla/dt/12464
Subject Headings: Image processing, Face perception, Neural networks (Computer science)
Format: Document (PDF)

Title: An intelligent system for predicting bridge condition rating.
Creator: Thiruppathi, Arulseelan., Florida Atlantic University, Pandya, Abhijit S., College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
Abstract/Description: A neural network based model for prediction of bridge condition rating is proposed. The back-propagation algorithm is used to train the network to recognize the pattern of deterioration of bridges and use this knowledge in predicting the future condition rating of a bridge. The various factors which influence the deterioration rate are considered as input to the system. The model then predicts the condition rating of the three major sub-components of a bridge viz. the deck, sub-structure and...
Show moreA neural network based model for prediction of bridge condition rating is proposed. The back-propagation algorithm is used to train the network to recognize the pattern of deterioration of bridges and use this knowledge in predicting the future condition rating of a bridge. The various factors which influence the deterioration rate are considered as input to the system. The model then predicts the condition rating of the three major sub-components of a bridge viz. the deck, sub-structure and the super-structure. Fuzzy logic is used to evaluate the overall condition rating of the bridge using the condition rating of the components. To demonstrate the superiority of the neural network model over the traditional models, the history of the deterioration rates for the components were also considered in the prediction of their future condition. The proposed system is versatile and can be easily extended to include other parameters and updated from time to time without much effort.
Show less
Date Issued: 1994
PURL: http://purl.flvc.org/fcla/dt/15096
Subject Headings: Bridges--Maintenance and repair, Neural networks (Computer science)
Format: Document (PDF)

Title: Financial prediction using time series.
Creator: Srinivasan, Arunkumar., Florida Atlantic University, Pandya, Abhijit S., College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
Abstract/Description: This thesis discusses the implementation of a feed forward NN using time series model to predict the sudden rise or sudden crash of a company's stock prices. The theory behind this prediction system is Pattern recognition. Pattern recognition techniques for time-series prediction are based on structural matching of the current state of the time-series with previously occurring states in historical data for making predictions. This study reports the result of attempts to predict the Motorola...
Show moreThis thesis discusses the implementation of a feed forward NN using time series model to predict the sudden rise or sudden crash of a company's stock prices. The theory behind this prediction system is Pattern recognition. Pattern recognition techniques for time-series prediction are based on structural matching of the current state of the time-series with previously occurring states in historical data for making predictions. This study reports the result of attempts to predict the Motorola stock price index using artificial neural networks (ANN). Daily data from January 1999 to December 2001 were taken from the NYSE. These data are classified based on criteria of an n% fall or rise of price corresponding to the previous day close price. A novel method using Hurst exponent is used in selecting the data set. These data are fed into a Back Propagated Neural Network. The number of hidden layers and number of neurons are systematically selected to implement a better predicting machine. The implemented model is tested using both interpolated and extrapolated data. Fundamental limitations and inherent difficulties when using neural networks for processing of high noise, small sample size signals are also discussed. Results of the prediction are presented and an elaborate discussion is made comparing the results.
Show less
Date Issued: 2003
PURL: http://purl.flvc.org/fcla/dt/13045
Subject Headings: Pattern recognition systems, Neural networks (Computer science), Stock exchanges
Format: Document (PDF)

Title: A new GMDH type algorithm for the development of neural networks for pattern recognition.
Creator: Gilbar, Thomas C., Florida Atlantic University, Pandya, Abhijit S., College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
Abstract/Description: Researchers from a wide range of fields have discovered the benefits of applying neural networks to pattern recognition problems. Although applications for neural networks have increased, development of tools to design these networks has been slower. There are few comprehensive network development methods. Those that do exist are slow, inefficient, and application specific, require predetermination of the final network structure, and/or result in large, complicated networks. Finding optimal...
Show moreResearchers from a wide range of fields have discovered the benefits of applying neural networks to pattern recognition problems. Although applications for neural networks have increased, development of tools to design these networks has been slower. There are few comprehensive network development methods. Those that do exist are slow, inefficient, and application specific, require predetermination of the final network structure, and/or result in large, complicated networks. Finding optimal neural networks that balance low network complexity with accuracy is a complicated process that traditional network development procedures are incapable of achieving. Although not originally designed for neural networks, the Group Method of Data Handling (GMDH) has characteristics that are ideal for neural network design. GMDH minimizes the number of required neurons by choosing and keeping only the best neurons and filtering out unneeded inputs. In addition, GMDH develops the neurons and organizes the network simultaneously, saving time and processing power. However, some of the qualities of the network must still be predetermined. This dissertation introduces a new algorithm that applies some of the best characteristics of GMDH to neural network design. The new algorithm is faster, more flexible, and more accurate than traditional network development methods. It is also more dynamic than current GMDH based methods, capable of creating a network that is optimal for an application and training data. Additionally, the new algorithm virtually guarantees that the number of neurons progressively decreases in each succeeding layer. To show its flexibility, speed, and ability to design optimal networks, the algorithm was used to successfully design networks for a wide variety of real applications. The networks developed using the new algorithm were compared to other development methods and network architectures. The new algorithm's networks were more accurate and yet less complicated than the other networks. Additionally, the algorithm designs neurons that are flexible enough to meet the needs of the specific applications, yet similar enough to be implemented using a standardized hardware cell. When combined with the simplified network layout that naturally occurs with the algorithm, this results in networks that can be implemented using Field Programmable Gate Array (FPGA) type devices.
Show less
Date Issued: 2002
PURL: http://purl.flvc.org/fcla/dt/11994
Subject Headings: GMDH algorithms, Neural networks (Computer science), Pattern recognition systems
Format: Document (PDF)

Title: OPTIMIZED DEEP LEARNING ARCHITECTURES AND TECHNIQUES FOR EDGE AI.
Creator: Zaniolo, Luiz, Marques, Oge, Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
Abstract/Description: The recent rise of artificial intelligence (AI) using deep learning networks allowed the development of automatic solutions for many tasks that, in the past, were seen as impossible to be performed by a machine. However, deep learning models are getting larger, need significant processing power to train, and powerful machines to use it. As deep learning applications become ubiquitous, another trend is taking place: the growing use of edge devices. This dissertation addresses selected...
Show moreThe recent rise of artificial intelligence (AI) using deep learning networks allowed the development of automatic solutions for many tasks that, in the past, were seen as impossible to be performed by a machine. However, deep learning models are getting larger, need significant processing power to train, and powerful machines to use it. As deep learning applications become ubiquitous, another trend is taking place: the growing use of edge devices. This dissertation addresses selected technical issues associated with edge AI, proposes novel solutions to them, and demonstrates the effectiveness of the proposed approaches. The technical contributions of this dissertation include: (i) architectural optimizations to deep neural networks, particularly the use of patterned stride in convolutional neural networks used for image classification; (ii) use of weight quantization to reduce model size without hurting its accuracy; (iii) systematic evaluation of the impact of image imperfections on skin lesion classifiers' performance in the context of teledermatology; and (iv) a new approach for code prediction using natural language processing techniques, targeted at edge devices.
Show less
Date Issued: 2021
PURL: http://purl.flvc.org/fau/fd/FA00013822
Subject Headings: Artificial intelligence, Deep learning (Machine learning), Neural networks (Computer science)
Format: Document (PDF)

Title: Software reliability engineering: An evolutionary neural network approach.
Creator: Hochman, Robert., Florida Atlantic University, Khoshgoftaar, Taghi M.
Abstract/Description: This thesis presents the results of an empirical investigation of the applicability of genetic algorithms to a real-world problem in software reliability--the fault-prone module identification problem. The solution developed is an effective hybrid of genetic algorithms and neural networks. This approach (ENNs) was found to be superior, in terms of time, effort, and confidence in the optimality of results, to the common practice of searching manually for the best-performing net. Comparisons...
Show moreThis thesis presents the results of an empirical investigation of the applicability of genetic algorithms to a real-world problem in software reliability--the fault-prone module identification problem. The solution developed is an effective hybrid of genetic algorithms and neural networks. This approach (ENNs) was found to be superior, in terms of time, effort, and confidence in the optimality of results, to the common practice of searching manually for the best-performing net. Comparisons were made to discriminant analysis. On fault-prone, not-fault-prone, and overall classification, the lower error proportions for ENNs were found to be statistically significant. The robustness of ENNs follows from their superior performance over many data configurations. Given these encouraging results, it is suggested that ENNs have potential value in other software reliability problem domains, where genetic algorithms have been largely ignored. For future research, several plans are outlined for enhancing ENNs with respect to accuracy and applicability.
Show less
Date Issued: 1997
PURL: http://purl.flvc.org/fcla/dt/15474
Subject Headings: Neural networks (Computer science), Software engineering, Genetic algorithms
Format: Document (PDF)

Title: Studies on nonlinear activity and cross-entropy considerations in neural networks.
Creator: Abusalah, Salahalddin Tawfiq., Florida Atlantic University, Neelakanta, Perambur S., College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
Abstract/Description: The objectives of this research as deliberated in this dissertation are two-folded: (i) To study the nonlinear activity in the neural complex (real and artificial) and (ii) to analyze the learning processe(s) pertinent to an artificial neural network in the information-theoretic plane using cross-entropy error-metrics. The research efforts envisaged enclave the following specific tasks: (i) Obtaining a general solution for the Bernoulli-Riccati equation to represent a single parameter family...
Show moreThe objectives of this research as deliberated in this dissertation are two-folded: (i) To study the nonlinear activity in the neural complex (real and artificial) and (ii) to analyze the learning processe(s) pertinent to an artificial neural network in the information-theoretic plane using cross-entropy error-metrics. The research efforts envisaged enclave the following specific tasks: (i) Obtaining a general solution for the Bernoulli-Riccati equation to represent a single parameter family of S-shaped (sigmoidal) curves depicting the nonlinear activity in the neural network. (ii) Analysis of the logistic growth of output versus input values in the neural complex (real and artificial) under the consideration that the boundaries of the sets constituting the input and output entities are crisp and/or fuzzy. (iii) Construction of a set of cross-entropy error-metrics (known as Csiszar's measures) deduced in terms of the parameters pertinent to a perceptron topology and elucidation of their relative effectiveness in training the network optimally towards convergence. (iv) Presenting the methods of symmetrizing and balancing the aforesaid error-entropy measures (in the information-theoretic plane) so as to make them usable as error-metrics in the test domain. (v) Description and analysis of the dynamics of neural learning process in the information-theoretic plane for both crisp and fuzzy attributes of input values. Relevant to these topics portraying the studies on nonlinear activity and cross-entropy considerations vis-a-vis neural networks, newer and/or exploratory inferences are made, logical conclusions are enumerated and relative discussions are presented along with the scope for future research to be pursued.
Show less
Date Issued: 1996
PURL: http://purl.flvc.org/fcla/dt/12447
Subject Headings: Neural networks (Computer science), Entropy (Information theory), Nonlinear control theory
Format: Document (PDF)

Title: Stochastical aspects of neuronal activity, neural networks, and communication.
Creator: De Groff, Dolores F., Florida Atlantic University, Neelakanta, Perambur S., College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
Abstract/Description: By revisiting the popular framework of depicting neuronal (collective) activities as analogous to Ising's spin-glass theory of interacting magnetic spins, the contradictions that coexist with such an analogy are extracted and discussed. To alleviate such contradictions, an alternative strategy of equating the neuronal interactions to the partially anisotropic nematic phase of disorder pertaining to liquid crystals is proposed. Hence, the extent of anisotropy in the neuronal system, quantified...
Show moreBy revisiting the popular framework of depicting neuronal (collective) activities as analogous to Ising's spin-glass theory of interacting magnetic spins, the contradictions that coexist with such an analogy are extracted and discussed. To alleviate such contradictions, an alternative strategy of equating the neuronal interactions to the partially anisotropic nematic phase of disorder pertaining to liquid crystals is proposed. Hence, the extent of anisotropy in the neuronal system, quantified in terms of an order-function, is specified to elucidate the nonlinear squashing action of the input-output relations in a neuronal cell. The relevant approach thereof, is based on Langevin's theory considerations as applied to dipole molecules. Further, in view of the stochastical properties due to the inherent disorder associated with the neuronal assembly, the progression of state-transitions across the interconnected cells is modeled as a momentum flow relevant to particle dynamics. Hence, corresponding wave mechanics attributions of such a collective movement of state-transition activity are described in terms of a probabilistic wave function. Lastly, the stochastical aspects of noise-perturbed neuronal dynamics are studied via Fokker-Planck equation representing the Langevin-type relaxational (nonlinear) process associated with the neuronal states. On each of these topics portraying the stochastical characteristics of the neuronal assembly and its activities, newer and/or more exploratory inferences are made, logical conclusions are enumerated and relevant discussions are presented along with the scope for future research to be pursued.
Show less
Date Issued: 1993
PURL: http://purl.flvc.org/fcla/dt/12326
Subject Headings: Neurons--Mathematical models, Stochastic processes, Neural networks (Computer science)
Format: Document (PDF)

Title: Using a cerebellar model arithmetic computer (CMAC) neural network to control an autonomous underwater vehicle.
Creator: Comoglio, Rick F., Florida Atlantic University, Pandya, Abhijit S.
Abstract/Description: The design of an Autonomous Undersea Vehicle (AUV) control system is a significant challenge in-light of the highly uncertain nature of the ocean environment together with partially known nonlinear vehicle dynamics. This thesis describes a Neural Network architecture called Cerebellar Model Arithmetic Computer (CMAC). CMAC is used to control a model of an Autonomous Underwater Vehicle. The AUV model consists of two input parameters, the rudder and stern plane deflections, controlling six...
Show moreThe design of an Autonomous Undersea Vehicle (AUV) control system is a significant challenge in-light of the highly uncertain nature of the ocean environment together with partially known nonlinear vehicle dynamics. This thesis describes a Neural Network architecture called Cerebellar Model Arithmetic Computer (CMAC). CMAC is used to control a model of an Autonomous Underwater Vehicle. The AUV model consists of two input parameters, the rudder and stern plane deflections, controlling six output parameters; forward velocity, vertical velocity, pitch angle, side velocity, roll angle, and yaw angle. Properties of CMAC and results of computer simulations for identification and control of the AUV model are presented.
Show less
Date Issued: 1991
PURL: http://purl.flvc.org/fcla/dt/14762
Subject Headings: Neural networks (Computer science), Artificial intelligence, Submersibles--Automatic control
Format: Document (PDF)

Title: Prediction of Radiobiological Indices and Equivalent Uniform Dose in Lung Cancer Radiation Therapy using an Artificial Neural Network.
Creator: Pudasaini, Mukunda Prasad, Leventouri, Theodora, Muhammad, Wazir, Florida Atlantic University, Department of Physics, Charles E. Schmidt College of Science
Abstract/Description: In radiotherapy, radiobiological indices tumor control probability (TCP), normal tissue complication probability (NTCP), and equivalent uniform dose (EUD) are computed by analytical models. These models are rarely employed to rank and optimize treatment plans even though radiobiological indices weights more compared to dosimetric indices to reflect treatment goal. The objective of this study is to predict TCP, NTCP and EUDs for lung cancer radiotherapy treatment plans using an artificial...
Show moreIn radiotherapy, radiobiological indices tumor control probability (TCP), normal tissue complication probability (NTCP), and equivalent uniform dose (EUD) are computed by analytical models. These models are rarely employed to rank and optimize treatment plans even though radiobiological indices weights more compared to dosimetric indices to reflect treatment goal. The objective of this study is to predict TCP, NTCP and EUDs for lung cancer radiotherapy treatment plans using an artificial neural network (ANN). A total of 100 lung cancer patients’ treatment plans were selected for this study. Normal tissue complication probability (NTCP) of organs at risk (OARs) i.e., esophagus, spinal cord, heart and contralateral lung and tumor control probability (TCP) of treatment target volume (i.e., tumor) were calculated by the equivalent uniform dose (EUD) model. TCP/NTCP pairing with corresponding EUD are used individually as outputs for the neural network. The inputs for ANN are planning target volume (PTV), treatment modality, tumor location, prescribed dose, number of fractions, mean dose to PTV, gender, age, and mean doses to the OARs. The ANN is based on Levenberg-Marquardt algorithm with one hidden layer having 13 inputs and 2 outputs. 70% of the data was used for training, 15% for validation and 15% for testing the ANN. Our ANN model predicted TCP and EUD with correlation coefficient of 0.99 for training, 0.96 for validation, and 0.94 for testing. In NTCP and EUD prediction, averages of correlation coefficients are 0.94 for training, 0.89 for validation and 0.84 for testing. The maximum mean squared error (MSE) for the ANN is 0.025 in predicting the NTCP and EUD of heart. Our results show that an ANN model can be used with high discriminatory power to predict the radiobiological indices for lung cancer treatment plans.
Show less
Date Issued: 2022
PURL: http://purl.flvc.org/fau/fd/FA00014064
Subject Headings: Lungs--Cancer--Radiotherapy, Radiobiology, Neural networks (Computer science)
Format: Document (PDF)

Title: COMPUTATION IN SELF-ATTENTION NETWORKS.
Creator: Morris, Paul, Barenholtz, Elan, Florida Atlantic University, Center for Complex Systems and Brain Sciences, Charles E. Schmidt College of Science
Abstract/Description: Neural network models with many tunable parameters can be trained to approximate functions that transform a source distribution, or dataset, into a target distribution of interest. In contrast to low-parameter models with simple governing equations, the dynamics of transformations learned in deep neural network models are abstract and the correspondence of dynamical structure to predictive function is opaque. Despite their “black box” nature, neural networks converge to functions that...
Show moreNeural network models with many tunable parameters can be trained to approximate functions that transform a source distribution, or dataset, into a target distribution of interest. In contrast to low-parameter models with simple governing equations, the dynamics of transformations learned in deep neural network models are abstract and the correspondence of dynamical structure to predictive function is opaque. Despite their “black box” nature, neural networks converge to functions that implement complex tasks in computer vision, Natural Language Processing (NLP), and the sciences when trained on large quantities of data. Where traditional machine learning approaches rely on clean datasets with appropriate features, sample densities, and label distributions to mitigate unwanted bias, modern Transformer neural networks with self-attention mechanisms use Self-Supervised Learning (SSL) to pretrain on large, unlabeled datasets scraped from the internet without concern for data quality. SSL tasks have been shown to learn functions that match or outperform their supervised learning counterparts in many fields, even without task-specific finetuning. The recent paradigm shift to pretraining large models with massive amounts of unlabeled data has given credibility to the hypothesis that SSL pretraining can produce functions that implement generally intelligent computations.
Show less
Date Issued: 2022
PURL: http://purl.flvc.org/fau/fd/FA00014061
Subject Headings: Neural networks (Computer science), Machine learning, Self-supervised learning
Format: Document (PDF)

Title: EMBEDDING LEARNING FOR COMPLEX DYNAMIC INFORMATION NETWORKS.
Creator: Wu, Man, Zhu, Xingquan, Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
Abstract/Description: With the rapid development of networking platforms and data intensive applications, networks (or graphs) are becoming convenient and fundamental tools to model the complex inter-dependence among big scale data. As a result, networks (or graphs) are being widely used in many applications, including citation networks [40], social media networks [71], and so on. However, the high complexity (containing many important information) as well as the dynamic nature of the network makes the graph...
Show moreWith the rapid development of networking platforms and data intensive applications, networks (or graphs) are becoming convenient and fundamental tools to model the complex inter-dependence among big scale data. As a result, networks (or graphs) are being widely used in many applications, including citation networks [40], social media networks [71], and so on. However, the high complexity (containing many important information) as well as the dynamic nature of the network makes the graph learning task more difficult. To have better graph representations (capture both node content and graph structure), many research efforts have been made to develop reliable and efficient algorithms. Therefore, the good graph representation learning is the key factor in performing well on downstream tasks. The dissertation mainly focuses on the graph representation learning, which aims to embed both structure and node content information of graphs into a compact and low dimensional space for a new representation learning. More specifically, in order to achieve an efficient and robust graph representation, the following four problems will be studied from different perspectives: 1) We study the problem of positive unlabeled graph learning for network node classification, and present a new deep learning model as a solution; 2) We formulate a new open-world learning problem for graph data, and propose an uncertain node representation learning approach and sampling strategy to solve the problem; 3) For cross-domain graph learning, we present a novel unsupervised graph domain adaptation problem, and propose an effective graph convolutional network algorithm to solve it; 4) We consider a dynamic graph as a network with changing nodes and edges in temporal order and propose a temporal adaptive aggregation network (TAAN) for dynamic graph learning. Finally, the proposed models are verified and evaluated on various real-world datasets.
Show less
Date Issued: 2022
PURL: http://purl.flvc.org/fau/fd/FA00014066
Subject Headings: Neural networks (Computer science), Machine learning, Graphs, Embeddings (Mathematics)
Format: Document (PDF)

Title: TOWARDS SELF-ORGANIZED BRAIN: TOPOLOGICAL REINFORCEMENT LEARNING WITH GRAPH CELLULAR AUTOMATA.
Creator: Ray, Subhosit, Barenholtz, Elan, Florida Atlantic University, Department of Psychology, Charles E. Schmidt College of Science
Abstract/Description: Automatizing optimal neural architectures is an under-explored domain; the majority of deep learning domains base their architecture on multiplexing different well-known architectures together based on past studies. Even after extensive research, the deployed algorithms may only work for specific domains, provide a minor boost, or even underperform compared to the previous state-of-the-art implementations. One approach, Neural architecture search, requires generating a pool of network...
Show moreAutomatizing optimal neural architectures is an under-explored domain; the majority of deep learning domains base their architecture on multiplexing different well-known architectures together based on past studies. Even after extensive research, the deployed algorithms may only work for specific domains, provide a minor boost, or even underperform compared to the previous state-of-the-art implementations. One approach, Neural architecture search, requires generating a pool of network topologies based on well-known kernel and activation functions. However, iteratively training the generated topologies and creating newer topologies based on the best-performing ones is computationally expensive and out of scope for most academic labs. In addition, the search space is constrained to the predetermined dictionary of kernel functions to generate the topologies. This thesis considers neural networks as a weighted directed graph, incorporating the ideas of message passing in graph neural networks to propagate the information from the input to the output nodes. We show that such a method relieves the dependency on a search space constrained to well-known kernel functions over any arbitrary graph structures. We test our algorithms in the RL environment and explore several optimization forays, such as graph attention and PPO to let us solve the problem. We improve upon the slow convergence of PPO using Neural CA approach as a self-organizing overhead towards generating adjacency matrices of network topologies. This exploration towards indirect encoding (an abstraction of DNA in neuro-developmental biology) yielded a much faster algorithm for convergence. In addition, we introduce 1D-involution as a way to implement message passing across nodes in a graph, which further reduces the parameter space to a significant degree without hindering performance.
Show less
Date Issued: 2024
PURL: http://purl.flvc.org/fau/fd/FA00014436
Subject Headings: Neural networks (Computer science), Reinforcement learning, Cellular automata
Format: Document (PDF)

Title: COMPARISON OF CLASSIFYING HUMAN ACTIONS FROM BIOLOGICAL MOTION WITH ARTIFICIAL NEURAL NETWORKS.
Creator: Wong, Rachel, Barenholtz, Elan, Florida Atlantic University, Department of Psychology, Charles E. Schmidt College of Science
Abstract/Description: The ability to recognize human actions is essential for individuals to navigate through their daily life. Biological motion is the primary mechanism people use to recognize actions quickly and efficiently, but their precision can vary. The development of Artificial Neural Networks (ANNs) has the potential to enhance the efficiency and effectiveness of accomplishing common human tasks, including action recognition. However, the performance of ANNs in action recognition depends on the type of...
Show moreThe ability to recognize human actions is essential for individuals to navigate through their daily life. Biological motion is the primary mechanism people use to recognize actions quickly and efficiently, but their precision can vary. The development of Artificial Neural Networks (ANNs) has the potential to enhance the efficiency and effectiveness of accomplishing common human tasks, including action recognition. However, the performance of ANNs in action recognition depends on the type of model used. This study aimed to improve the accuracy of ANNs in action classification by incorporating biological motion information into the input conditions. The study used the UCF Crime dataset, a dataset containing surveillance videos of normal and criminal activity, and extracted biological motion information with OpenPose, a pose estimation ANN. OpenPose adjusted to create four condition types using the biological motion information (image-only, image with biological motion, only biological motion, and coordinates only) and used either a 3-Dimensional Convolutional Neural Network (3D CNN) or a Gated Recurrent Unit (GRU) to classify the actions. Overall, the study found that including biological motion information in the input conditions led to higher accuracy regardless of the number of action categories in the dataset. Moreover, the GRU model using the 'coordinates only' condition had the best accuracy out of all the action classification models. These findings suggest that incorporating biological motion into input conditions and using numerical format input data can benefit the development of accurate action classification models using ANNs.
Show less
Date Issued: 2023
PURL: http://purl.flvc.org/fau/fd/FA00014164
Subject Headings: Neural networks (Computer science), Human activity recognition, Artificial intelligence
Format: Document (PDF)

Title: AI COMPUTATION OF L1-NORM-ERROR PRINCIPAL COMPONENTS WITH APPLICATIONS TO TRAINING DATASET CURATION AND DETECTION OF CHANGE.
Creator: Varma, Kavita, Pados, Dimitris, Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
Abstract/Description: The aim of this dissertation is to achieve a thorough understanding and develop an algorithmic framework for a crucial aspect of autonomous and artificial intelligence (AI) systems: Data Analysis. In the current era of AI and machine learning (ML), ”data” holds paramount importance. For effective learning tasks, it is essential to ensure that the training dataset is accurate and comprehensive. Additionally, during system operation, it is vital to identify and address faulty data to prevent...
Show moreThe aim of this dissertation is to achieve a thorough understanding and develop an algorithmic framework for a crucial aspect of autonomous and artificial intelligence (AI) systems: Data Analysis. In the current era of AI and machine learning (ML), ”data” holds paramount importance. For effective learning tasks, it is essential to ensure that the training dataset is accurate and comprehensive. Additionally, during system operation, it is vital to identify and address faulty data to prevent potentially catastrophic system failures. Our research in data analysis focuses on creating new mathematical theories and algorithms for outlier-resistant matrix decomposition using L1-norm principal component analysis (PCA). L1-norm PCA has demonstrated robustness against irregular data points and will be pivotal for future AI learning and autonomous system operations. This dissertation presents a comprehensive exploration of L1-norm techniques and their diverse applications. A summary of our contributions in this manuscript follows: Chapter 1 establishes the foundational mathematical notation and linear algebra concepts critical for the subsequent discussions, along with a review of the complexities of the current state-of-the-art in L1-norm matrix decomposition algorithms. In Chapter 2, we address the L1-norm error decomposition problem by introducing a novel method called ”Individual L1-norm-error Principal Component Computation by 3-layer Perceptron” (Perceptron L1 error). Extensive studies demonstrate the efficiency of this greedy L1-norm PC calculator.
Show less
Date Issued: 2024
PURL: http://purl.flvc.org/fau/fd/FA00014460
Subject Headings: Artificial intelligence, Machine learning, Neural networks (Computer science), Data Analysis
Format: Document (PDF)

Title: An Exploration into Synthetic Data and Generative Aversarial Networks.
Creator: Shorten, Connor M., Khoshgoftaar, Taghi M., Florida Atlantic University, College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
Abstract/Description: This Thesis surveys the landscape of Data Augmentation for image datasets. Completing this survey inspired further study into a method of generative modeling known as Generative Adversarial Networks (GANs). A survey on GANs was conducted to understood recent developments and the problems related to training them. Following this survey, four experiments were proposed to test the application of GANs for data augmentation and to contribute to the quality improvement in GAN-generated data....
Show moreThis Thesis surveys the landscape of Data Augmentation for image datasets. Completing this survey inspired further study into a method of generative modeling known as Generative Adversarial Networks (GANs). A survey on GANs was conducted to understood recent developments and the problems related to training them. Following this survey, four experiments were proposed to test the application of GANs for data augmentation and to contribute to the quality improvement in GAN-generated data. Experimental results demonstrate the effectiveness of GAN-generated data as a pre-training metric. The other experiments discuss important characteristics of GAN models such as the refining of prior information, transferring generative models from large datasets to small data, and automating the design of Deep Neural Networks within the context of the GAN framework. This Thesis will provide readers with a complete introduction to Data Augmentation and Generative Adversarial Networks, as well as insights into the future of these techniques.
Show less
Date Issued: 2019
PURL: http://purl.flvc.org/fau/fd/FA00013263
Subject Headings: Neural networks (Computer science), Computer vision, Images, Generative adversarial networks, Data sets
Format: Document (PDF)

Title: MULTIFACETED EMBEDDING LEARNING FOR NETWORKED DATA AND SYSTEMS.
Creator: Shi, Min, Tang, Yufei, Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
Abstract/Description: Network embedding or representation learning is important for analyzing many real-world applications and systems, i.e., social networks, citation networks and communication networks. It targets at learning low-dimensional vector representations of nodes with preserved graph structure (e.g., link relations) and content (e.g., texts) information. The derived node representations can be directly applied in many downstream applications, including node classification, clustering and visualization....
Show moreNetwork embedding or representation learning is important for analyzing many real-world applications and systems, i.e., social networks, citation networks and communication networks. It targets at learning low-dimensional vector representations of nodes with preserved graph structure (e.g., link relations) and content (e.g., texts) information. The derived node representations can be directly applied in many downstream applications, including node classification, clustering and visualization. In addition to the complex network structures, nodes may have rich non structure information such as labels and contents. Therefore, structure, label and content constitute different aspects of the entire network system that reflect node similarities from multiple complementary facets. This thesis focuses on multifaceted network embedding learning, which aims to efficiently incorporate distinct aspects of information such as node labels and node contents for cooperative low-dimensional representation learning together with node topology.
Show less
Date Issued: 2020
PURL: http://purl.flvc.org/fau/fd/FA00013516
Subject Headings: Embedded computer systems, Neural networks (Computer science), Network embedding, Machine learning
Format: Document (PDF)

Title: NEURALSYNTH - A NEURAL NETWORK TO FPGA COMPILATION FRAMEWORK FOR RUNTIME EVALUATION.
Creator: Lanham, Grant Jr, Hallstrom, Jason O., Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
Abstract/Description: Artificial neural networks are increasing in power, with attendant increases in demand for efficient processing. Performance is limited by clock speed and degree of parallelization available through multi-core processors and GPUs. With a design tailored to a specific network, a field-programmable gate array (FPGA) can be used to minimize latency without the need for geographically distributed computing. However, the task of programming an FPGA is outside the realm of most data scientists....
Show moreArtificial neural networks are increasing in power, with attendant increases in demand for efficient processing. Performance is limited by clock speed and degree of parallelization available through multi-core processors and GPUs. With a design tailored to a specific network, a field-programmable gate array (FPGA) can be used to minimize latency without the need for geographically distributed computing. However, the task of programming an FPGA is outside the realm of most data scientists. There are tools to program FPGAs from a high level description of a network, but there is no unified interface for programmers across these tools. In this thesis, I present the design and implementation of NeuralSynth, a prototype Python framework which aims to bridge the gap between data scientists and FPGA programming for neural networks. My method relies on creating an extensible Python framework that is used to automate programming and interaction with an FPGA. The implementation includes a digital design for the FPGA that is completed by a Python framework. Programming and interacting with the FPGA does not require leaving the Python environment. The extensible approach allows multiple implementations, resulting in a similar workflow for each implementation. For evaluation, I compare the results of my implementation with a known neural network framework.
Show less
Date Issued: 2020
PURL: http://purl.flvc.org/fau/fd/FA00013533
Subject Headings: Artificial neural networks, Neural networks (Computer science)--Design, Field programmable gate arrays, Python (Computer program language)
Format: Document (PDF)

Title: DEEP LEARNING BASED ANOMALY DETECTION IN SPACE SYSTEMS AND OPERATIONS.
Creator: Akbarian, Hamid, Mahgoub, Imadeldin, Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
Abstract/Description: The relentless expansion of space exploration necessitates the development of robust and dependable anomaly detection systems (ADS) to safeguard the safety and efficacy of space missions. Conventional anomaly detection methods often falter in the face of the intricate and nuanced dynamics of space systems, resulting in a proliferation of false positives and/or false negatives. In this study, we explore into cutting-edge techniques in deep learning (DL) to tackle the challenges inherent in ADS...
Show moreThe relentless expansion of space exploration necessitates the development of robust and dependable anomaly detection systems (ADS) to safeguard the safety and efficacy of space missions. Conventional anomaly detection methods often falter in the face of the intricate and nuanced dynamics of space systems, resulting in a proliferation of false positives and/or false negatives. In this study, we explore into cutting-edge techniques in deep learning (DL) to tackle the challenges inherent in ADS. This research offers an in-depth examination of recent breakthroughs and hurdles in deep learning-driven anomaly detection tailored specifically for space systems and operations. A key advantage of deep learning-based anomaly detection lies in its adaptability to the diverse data encountered in space missions. For instance, Convolutional Neural Networks (CNNs) excel at capturing spatial dependencies in high-dimensional data, rendering them well-suited for tasks such as satellite imagery analysis. Conversely, Recurrent Neural Networks (RNNs), with their temporal modeling prowess, excel in identifying anomalies in time-series data generated by spacecraft sensors. Despite the potential of deep learning, several challenges persist in its application to anomaly detection in space systems. The scarcity of labeled data presents a formidable hurdle, as acquiring labeled anomalies during space operations is often prohibitively expensive and impractical. Additionally, the interpretability of deep learning models remains a concern, particularly in mission-critical scenarios where human operators need to comprehend the rationale behind anomaly predictions.
Show less
Date Issued: 2024
PURL: http://purl.flvc.org/fau/fd/FA00014390
Subject Headings: Anomaly detection (Computer security), Outer space—Exploration, Deep learning (Machine learning), Neural networks (Computer science), Convolutional neural networks
Format: Document (PDF)

Title: Neural network approach to Bayesian background modeling for video object segmentation.
Creator: Culibrk, Dubravko., Florida Atlantic University, Furht, Borko, Marques, Oge, College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
Abstract/Description: Object segmentation in a video sequence is an essential task in video processing and forms the foundation of content analysis, scene understanding, object-based video encoding (e.g. MPEG-4), various surveillance and 2D-to-pseudo-3D conversion applications. Popularization and availability of video sequences with increased spatial resolution requires development of new, more efficient algorithms for object detection and segmentation. This dissertation discusses a novel neural-network-based...
Show moreObject segmentation in a video sequence is an essential task in video processing and forms the foundation of content analysis, scene understanding, object-based video encoding (e.g. MPEG-4), various surveillance and 2D-to-pseudo-3D conversion applications. Popularization and availability of video sequences with increased spatial resolution requires development of new, more efficient algorithms for object detection and segmentation. This dissertation discusses a novel neural-network-based approach to background modeling for motion-based object segmentation in video sequences. In particular, we show how Probabilistic Neural Network (PNN) architecture can be extended to form an unsupervised Bayesian classifier for the domain of video object segmentation. The constructed Background Modeling Neural Network (BNN) is capable of efficiently handling segmentation in natural-scene sequences with complex background motion and changes in illumination. The weights of the proposed neural network serve as an exclusive model of the background and are temporally updated to reflect the observed background statistics. The proposed approach is designed to enable an efficient, highly-parallelized hardware implementation. Such a system would be able to achieve real-time segmentation of high-resolution image sequences.
Show less
Date Issued: 2006
PURL: http://purl.flvc.org/fcla/dt/12214
Subject Headings: Neural networks (Computer science), Application software--Development, Data structures (Computer science), Bayesian field theory
Format: Document (PDF)

Neural networks (Computer science) (81)	+ -
Artificial intelligence (11)	+ -
Pattern recognition systems (9)	+ -
Machine learning (8)	+ -
Deep learning (Machine learning) (6)	+ -

Fuzzy logic (6)	+ -
GMDH algorithms (5)	+ -
Computer algorithms (4)	+ -
Image processing (4)	+ -
Time-series analysis (4)	+ -
Back propagation (Artificial intelligence) (3)	+ -
Genetic algorithms (3)	+ -
Packet switching (Data transmission) (3)	+ -
Software engineering (3)	+ -
Submersibles--Automatic control (3)	+ -
Artificial intelligence. (2)	+ -
Artificial neural networks (2)	+ -
Asynchronous transfer mode (2)	+ -
Cognitive neuroscience. (2)	+ -
Computer vision (2)	+ -
Convolutional neural networks (2)	+ -
Deep Learning (2)	+ -
Machine learning--Technique (2)	+ -
Optical character recognition devices (2)	+ -
Pavements--Skid resistance (2)	+ -
Reinforcement learning (2)	+ -
Stock price forecasting (2)	+ -
System identification (2)	+ -
Adaptive control systems--Computer simulation (1)	+ -
Air--Pollution--Florida--Palm Beach County (1)	+ -

Florida Atlantic University (80)	+ -
College of Engineering and Computer Science (58)	+ -
Department of Computer and Electrical Engineering and Computer Science (49)	+ -
Pandya, Abhijit S. (22)	+ -
Charles E. Schmidt College of Science (15)	+ -

Department of Ocean and Mechanical Engineering (8)	+ -
Khoshgoftaar, Taghi M. (7)	+ -
Barenholtz, Elan (6)	+ -
Center for Complex Systems and Brain Sciences (5)	+ -
Department of Physics (5)	+ -
Neelakanta, Perambur S. (5)	+ -
Department of Mathematical Sciences (3)	+ -
Muhammad, Wazir (3)	+ -
De Groff, Dolores F. (2)	+ -
Department of Psychology (2)	+ -
Furht, Borko (2)	+ -
Hahn, William (2)	+ -
Jirsa, Viktor K. (2)	+ -
Marques, Oge (2)	+ -
Scarlatos, Panagiotis (Pete) D. (2)	+ -
Shankar, Ravi (2)	+ -
Sudhakar, Raghavan (2)	+ -
Zhuang, Hanqi (2)	+ -
Zilouchian, Ali (2)	+ -
Abusalah, Salahalddin Tawfiq. (1)	+ -
Akbarian, Hamid (1)	+ -
Alemrajabi, Mahsa Firouzabad (1)	+ -
An, Edgar (1)	+ -
Andrews, Whitney Angelica Johanna (1)	+ -
Assis, Raquel (1)	+ -

Document (PDF) (86)	+ -
Set of related objects (1)	+ -

Search In

Pages

Pages

Sort Results By:

Narrow results by:

Collection

Topical Subject

Genre

Type of Resource

Language

Creator

Format

Owner