Current Search: Electronic Thesis or Dissertation (x) » Neural networks (Computer science) (x) » Bressler, Steven L. (x)
View All Items
Pages
- Title
- ACCURATE DETECTION OF SELECTIVE SWEEPS WITH TRANSFER LEARNING.
- Creator
- Sigler, Priya, DeGiorgio, Michael, Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
- Abstract/Description
-
Positive natural selection leaves detectable, distinctive patterns in the genome in the form of a selective sweep. Identifying areas of the genome that have undergone selective sweeps is an area of high interest as it enables understanding of species and population evolution. Previous work has accomplished this by evaluating patterns within summary statistics computed across the genome and through application of machine learning techniques to raw population genomic data. When using raw...
Show morePositive natural selection leaves detectable, distinctive patterns in the genome in the form of a selective sweep. Identifying areas of the genome that have undergone selective sweeps is an area of high interest as it enables understanding of species and population evolution. Previous work has accomplished this by evaluating patterns within summary statistics computed across the genome and through application of machine learning techniques to raw population genomic data. When using raw population genomic data, convolutional neural networks have most recently been employed as they can handle large input arrays and maintain correlations among elements. Yet, such models often require massive amounts of training data and can be computationally expensive to train for a given problem. Instead, transfer learning has recently been used in the image analysis literature to improve machine learning models by learning the important features of images from large unrelated datasets beforehand, and then refining these models through subsequent application on smaller and more relevant datasets. We combine transfer learning with convolutional neural networks to improve classification of selective sweeps from raw population genomic data. We show that the combination of transfer learning with convolutional neural networks allows for accurate classification of selective sweeps.
Show less - Date Issued
- 2021
- PURL
- http://purl.flvc.org/fau/fd/FA00013785
- Subject Headings
- Transfer learning (Machine learning), Neural networks (Computer science), Natural selection, Genomes
- Format
- Document (PDF)
- Title
- Activity analysis and detection of falling and repetitive motion.
- Creator
- Carryl, Clyde, College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
- Abstract/Description
-
This thesis examines the use of motion detection and analysis systems to detect falls and repetitive motion patterns of at-risk individuals. Three classes of motion are examined: Activities of daily living (ADL), falls, and repetitive motion. This research exposes a simple relationship between ADL and non-ADL movement, and shows how to use Principal Component Analysis and a kNN classifier to tell the 2 classes of motion apart with 100% sensitivity and specificity. It also identifies a more...
Show moreThis thesis examines the use of motion detection and analysis systems to detect falls and repetitive motion patterns of at-risk individuals. Three classes of motion are examined: Activities of daily living (ADL), falls, and repetitive motion. This research exposes a simple relationship between ADL and non-ADL movement, and shows how to use Principal Component Analysis and a kNN classifier to tell the 2 classes of motion apart with 100% sensitivity and specificity. It also identifies a more complex relationship between falls and repetitive motion, which both produce bodily accelerations exceeding 3G but differ with regard to their periodicity. This simplifies the classification problem of falls versus repetitive motion when taking into account that their data representations are similar except that repetitive motion displays a high degree of periodicity as compared to falls.
Show less - Date Issued
- 2013
- PURL
- http://purl.flvc.org/FAU/3360774
- Subject Headings
- Perpetual-motion processes, Human locomotion, Neural networks (Computer science), Artificial intelligence
- Format
- Document (PDF)
- Title
- An Application of Artificial Neural Networks for Hand Grip Classification.
- Creator
- Gosine, Robbie R., Zhuang, Hanqi, Florida Atlantic University
- Abstract/Description
-
The gripping action as performed by an average person is developed over their life and changes over time. The initial learning is based on trial and error and becomes a natural action which is modified as the physiology of the individual changes. Each grip type is a personal expression and as the grip changes over time to accommodate physiologically changes, it can be considered to be a grip-signature. lt is postulated that an ANN can deliver a classification mechanism that is able to make...
Show moreThe gripping action as performed by an average person is developed over their life and changes over time. The initial learning is based on trial and error and becomes a natural action which is modified as the physiology of the individual changes. Each grip type is a personal expression and as the grip changes over time to accommodate physiologically changes, it can be considered to be a grip-signature. lt is postulated that an ANN can deliver a classification mechanism that is able to make sense of the varying gripping inputs that are linearly inseparable and uniquely attributed to user physiology. Succinctly, in this design, the stifnulus is characterized by a voltage that represents the applied force in a grip. This signature of forces is then used to train an ANN to recognize the grip that produced the signature, the ANN in turn is used to successfully classify three unique states of grip-signatures collected from the gripping action of various individuals as they hold, lift and crush a paper coffee-cup. A comparative study is done for three types of classification: K-Means, Backpropagation Feedforward Neural Networks and Recurrent Neural Networks, with recommendations made in selecting more effective classification methods.
Show less - Date Issued
- 2007
- PURL
- http://purl.flvc.org/fau/fd/FA00012522
- Subject Headings
- Neural networks (Computer science), Pattern perception, Back propagation (Artificial intelligence), Multivariate analysis (Computer programs)
- 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
- An artificial neural network architecture for interpolation, function approximation, time series modeling and control applications.
- Creator
- Luebbers, Paul Glenn., Florida Atlantic University, Pandya, Abhijit S., Sudhakar, Raghavan, College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
- Abstract/Description
-
A new artificial neural network architecture called Power Net (PWRNET) and Orthogonal Power Net (OPWRNET) has been developed. Based on the Taylor series expansion of the hyperbolic tangent function, this novel architecture can approximate multi-input multi-layer artificial networks, while requiring only a single layer of hidden nodes. This allows a compact network representation with only one layer of hidden layer weights. The resulting trained network can be expressed as a polynomial...
Show moreA new artificial neural network architecture called Power Net (PWRNET) and Orthogonal Power Net (OPWRNET) has been developed. Based on the Taylor series expansion of the hyperbolic tangent function, this novel architecture can approximate multi-input multi-layer artificial networks, while requiring only a single layer of hidden nodes. This allows a compact network representation with only one layer of hidden layer weights. The resulting trained network can be expressed as a polynomial function of the input nodes. Applications which cannot be implemented with conventional artificial neural networks, due to their intractable nature, can be developed with these network architectures. The degree of nonlinearity of the network can be directly controlled by adjusting the number of hidden layer nodes, thus avoiding problems of over-fitting which restrict generalization. The learning algorithm used for adapting the network is the familiar error back propagation training algorithm. Other learning algorithms may be applied and since only one hidden layer is to be trained, the training performance of the network is expected to be comparable to or better than conventional multi-layer feed forward networks. The new architecture is explored by applying OPWRNET to classification, function approximation and interpolation problems. These applications show that the OPWRNET has comparable performance to multi-layer perceptrons. The OPWRNET was also applied to the prediction of noisy time series and the identification of nonlinear systems. The resulting trained networks, for system identification tasks, can be expressed directly as discrete nonlinear recursive polynomials. This characteristic was exploited in the development of two new neural network based nonlinear control algorithms, the Linearized Self-Tuning Controller (LSTC) and a variation of a Neural Adaptive Controller (NAC). These control algorithms are compared to a linear self-tuning controller and an artificial neural network based Inverse Model Controller. The advantages of these new controllers are discussed.
Show less - Date Issued
- 1994
- PURL
- http://purl.flvc.org/fcla/dt/12357
- Subject Headings
- Neural networks (Computer science)
- Format
- Document (PDF)
- Title
- Artificial neural network prediction of alluvial river geometry.
- Creator
- Hoffman, David Carl., Florida Atlantic University, Scarlatos, Panagiotis (Pete) D.
- Abstract/Description
-
An artificial neural network is used to predict the stable geometry of alluvial rivers. This knowledge is useful for the design of new channels or modification of natural rivers. Given inputs of river discharge, slope and mean particle size, an artificial neural network is trained to predict the corresponding stable channel width and depth. The network is trained using data from several alluvial canals and rivers. Various factors including training set size and composition, number of hidden...
Show moreAn artificial neural network is used to predict the stable geometry of alluvial rivers. This knowledge is useful for the design of new channels or modification of natural rivers. Given inputs of river discharge, slope and mean particle size, an artificial neural network is trained to predict the corresponding stable channel width and depth. The network is trained using data from several alluvial canals and rivers. Various factors including training set size and composition, number of hidden layer nodes, activation function type, and data scaling method are analyzed as variables affecting network performance. These factors are studied to determine impacts on network accuracy and generalizing ability.
Show less - Date Issued
- 1995
- PURL
- http://purl.flvc.org/fcla/dt/15179
- Subject Headings
- Alluvial streams, Neural networks (Computer science), Back propagation (Artificial intelligence), Sediment transport--Computer programs
- Format
- Document (PDF)
- Title
- Artificial neural network prediction of ground-level ozone concentration in Palm Beach County.
- Creator
- Crumiere, Mylene., Florida Atlantic University, Scarlatos, Panagiotis (Pete) D.
- Abstract/Description
-
The purpose of this study was to develop a user-friendly mathematical model for prediction of daily, ground level ozone concentration in Palm Beach County, Florida. The focus of this project was to investigate the correlation between hourly ozone concentrations and pre-existing pollutant levels and meteorological data. An artificial neural network model was applied, involving a backpropagation algorithm and the tangent sigmoid as the transfer function. Surface meteorological data and upper...
Show moreThe purpose of this study was to develop a user-friendly mathematical model for prediction of daily, ground level ozone concentration in Palm Beach County, Florida. The focus of this project was to investigate the correlation between hourly ozone concentrations and pre-existing pollutant levels and meteorological data. An artificial neural network model was applied, involving a backpropagation algorithm and the tangent sigmoid as the transfer function. Surface meteorological data and upper air data such as pressure, temperature, dew point temperature, wind speed and wind direction were included in the model, along with the ozone concentration in the hour previous to the forecast. Based on the model results, the 8-hour average ozone concentration is to be forecasted. This will assist state and local air pollution officials in providing the general public with early notice of an impending air quality problem.
Show less - Date Issued
- 1999
- PURL
- http://purl.flvc.org/fcla/dt/15723
- Subject Headings
- Neural networks (Computer science), Air--Pollution--Mathematical models, Air--Pollution--Florida--Palm Beach County, Ozone--Forecasting
- Format
- Document (PDF)
- Title
- A BCU scalable sensory acquisition system for EEG embedded applications.
- Creator
- Fathalla, Sherif S., College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
- Abstract/Description
-
Electroencephalogram (EEG) Recording has been through a lot of changes and modification since it was first introduced in 1929 due to rising technologies and signal processing advancements. The EEG Data acquisition stage is the first and most valuable component in any EEG recording System, it has the role of gathering and conditioning its input and outputting reliable data to be effectively analyzed and studied by digital signal processors using sophisticated and advanced algorithms which help...
Show moreElectroencephalogram (EEG) Recording has been through a lot of changes and modification since it was first introduced in 1929 due to rising technologies and signal processing advancements. The EEG Data acquisition stage is the first and most valuable component in any EEG recording System, it has the role of gathering and conditioning its input and outputting reliable data to be effectively analyzed and studied by digital signal processors using sophisticated and advanced algorithms which help in numerous medical and consumer applications. We have designed a low noise low power EEG data acquisition system that can be set to act as a standalone mobile EEG data processing unit providing data preprocessing functions; it can also be a very reliable high speed data acquisition interface to an EEG processing unit.
Show less - Date Issued
- 2010
- PURL
- http://purl.flvc.org/FAU/3164095
- Subject Headings
- Brain-computer interfaces, Computational neuroscience, Neural networks (Computer science)
- Format
- Document (PDF)
- Title
- BEHAVIORAL ANALYSIS OF DEEP CONVOLUTIONAL NEURAL NETWORKS FOR IMAGE CLASSIFICATION.
- Creator
- Clark, James Alex, Barenholtz, Elan, Florida Atlantic University, Center for Complex Systems and Brain Sciences, Charles E. Schmidt College of Science
- Abstract/Description
-
Within Deep CNNs there is great excitement over breakthroughs in network performance on benchmark datasets such as ImageNet. Around the world competitive teams work on new ways to innovate and modify existing networks, or create new ones that can reach higher and higher accuracy levels. We believe that this important research must be supplemented with research into the computational dynamics of the networks themselves. We present research into network behavior as it is affected by: variations...
Show moreWithin Deep CNNs there is great excitement over breakthroughs in network performance on benchmark datasets such as ImageNet. Around the world competitive teams work on new ways to innovate and modify existing networks, or create new ones that can reach higher and higher accuracy levels. We believe that this important research must be supplemented with research into the computational dynamics of the networks themselves. We present research into network behavior as it is affected by: variations in the number of filters per layer, pruning filters during and after training, collapsing the weight space of the trained network using a basic quantization, and the effect of Image Size and Input Layer Stride on training time and test accuracy. We provide insights into how the total number of updatable parameters can affect training time and accuracy, and how “time per epoch” and “number of epochs” affect network training time. We conclude with statistically significant models that allow us to predict training time as a function of total number of updatable parameters in the network.
Show less - Date Issued
- 2022
- PURL
- http://purl.flvc.org/fau/fd/FA00013940
- Subject Headings
- Neural networks (Computer science), Image processing
- Format
- Document (PDF)
- Title
- Brain Computer Interface And Neuroprosthetics.
- Creator
- Calderon, Rodrigo, Morgera, Salvatore D., Florida Atlantic University
- Abstract/Description
-
For many years people have consider the possibility that brain activity might provide a new channel for communication between a person's brain and the external world. Brain Computer Interface allows humans to control electronic devices using only their thoughts. The goal of this project is to provide the users with a basic control of a prosthetic arm using the signal acquired by an Electroencephalogram (EEG). The main objective of the research is to demonstrate and provide a system that...
Show moreFor many years people have consider the possibility that brain activity might provide a new channel for communication between a person's brain and the external world. Brain Computer Interface allows humans to control electronic devices using only their thoughts. The goal of this project is to provide the users with a basic control of a prosthetic arm using the signal acquired by an Electroencephalogram (EEG). The main objective of the research is to demonstrate and provide a system that allows individuals to obtain control of the device with very little training and very few electrodes. The research includes the development of an elaborate signal-processing algorithm that uses an Artificial Neural Network to determine the intentions of the user and their translation into commands to operate the prosthetic arm.
Show less - Date Issued
- 2007
- PURL
- http://purl.flvc.org/fau/fd/FA00012509
- Subject Headings
- Neural networks (Computer science), Pattern recognition systems, Prosthesis--Technological innovations, Artificial intelligence
- Format
- Document (PDF)
- Title
- A case study: Performance enhancement of nonlinear combinational optimization problem by neural networks.
- Creator
- Soni, Saurabh., Florida Atlantic University, Pandya, Abhijit S., College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
- Abstract/Description
-
Artificial Neural Networks have been widely used for obtaining solutions for combinational optimization problems. Traveling Salesman problem is a well known nonlinear combinational optimization problem. In Traveling Salesman problem, a fixed number of cities is given. An optimal tour of all these cities is required such that each city is visited only once and the total tour distance to be covered has to be minimized. Hopfield Networks have been applied for generating an optimal solution....
Show moreArtificial Neural Networks have been widely used for obtaining solutions for combinational optimization problems. Traveling Salesman problem is a well known nonlinear combinational optimization problem. In Traveling Salesman problem, a fixed number of cities is given. An optimal tour of all these cities is required such that each city is visited only once and the total tour distance to be covered has to be minimized. Hopfield Networks have been applied for generating an optimal solution. However there are certain factors which result in instability and local optimization of Hopfield Networks. In such cases the solutions obtained may not be optimal and feasible. In this thesis, the application of the K-Means algorithm is combined with the Hopfield Networks to generate more stable and optimum solutions to traveling salesperson problem.
Show less - Date Issued
- 2004
- PURL
- http://purl.flvc.org/fcla/dt/13108
- Subject Headings
- Neural networks (Computer science), Traveling-salesman problem
- 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
- COMPARISON OF PRE-TRAINED CONVOLUTIONAL NEURAL NETWORK PERFORMANCE ON GLIOMA CLASSIFICATION.
- Creator
- Andrews, Whitney Angelica Johanna, Furht, Borko, Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
- Abstract/Description
-
Gliomas are an aggressive class of brain tumors that are associated with a better prognosis at a lower grade level. Effective differentiation and classification are imperative for early treatment. MRI scans are a popular medical imaging modality to detect and diagnosis brain tumors due to its capability to non-invasively highlight the tumor region. With the rise of deep learning, researchers have used convolution neural networks for classification purposes in this domain, specifically pre...
Show moreGliomas are an aggressive class of brain tumors that are associated with a better prognosis at a lower grade level. Effective differentiation and classification are imperative for early treatment. MRI scans are a popular medical imaging modality to detect and diagnosis brain tumors due to its capability to non-invasively highlight the tumor region. With the rise of deep learning, researchers have used convolution neural networks for classification purposes in this domain, specifically pre-trained networks to reduce computational costs. However, with various MRI modalities, MRI machines, and poor image scan quality cause different network structures to have different performance metrics. Each pre-trained network is designed with a different structure that allows robust results given specific problem conditions. This thesis aims to cover the gap in the literature to compare the performance of popular pre-trained networks on a controlled dataset that is different than the network trained domain.
Show less - Date Issued
- 2020
- PURL
- http://purl.flvc.org/fau/fd/FA00013450
- Subject Headings
- Gliomas, Neural networks (Computer science), Deep Learning, Convolutional neural networks
- 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
- A connectionist approach to adaptive reasoning: An expert system to predict skid numbers.
- Creator
- Reddy, Mohan S., Florida Atlantic University, Pandya, Abhijit S., College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
- Abstract/Description
-
This project illustrates the neural network approach to constructing a fuzzy logic decision system. This technique employs an artificial neural network (ANN) to recognize the relationships that exit between the various inputs and outputs. An ANN is constructed based on the variables present in the application. The network is trained and tested. Various training methods are explored, some of which include auxiliary input and output columns. After successful testing, the ANN is exposed to new...
Show moreThis project illustrates the neural network approach to constructing a fuzzy logic decision system. This technique employs an artificial neural network (ANN) to recognize the relationships that exit between the various inputs and outputs. An ANN is constructed based on the variables present in the application. The network is trained and tested. Various training methods are explored, some of which include auxiliary input and output columns. After successful testing, the ANN is exposed to new data and the results are grouped into fuzzy membership sets based membership evaluation rules. This data grouping forms the basis of a new ANN. The network is now trained and tested with the fuzzy membership data. New data is presented to the trained network and the results form the fuzzy implications. This approach is used to compute skid resistance values from G-analyst accelerometer readings on open grid bridge decks.
Show less - Date Issued
- 1996
- PURL
- http://purl.flvc.org/fcla/dt/15239
- Subject Headings
- Artificial intelligence, Fuzzy logic, Neural networks (Computer science), Pavements--Skid resistance
- Format
- Document (PDF)
- Title
- CRACKING THE SPARSE CODE: LATERAL COMPETITION FORMS ROBUST V1-LIKE REPRESENTATIONS IN CONVOLUTIONAL NEURAL NETWORKS.
- Creator
- Teti, Michael, Barenholtz, Elan, Hahn, William, Florida Atlantic University, Center for Complex Systems and Brain Sciences, Charles E. Schmidt College of Science
- Abstract/Description
-
Although state-of-the-art Convolutional Neural Networks (CNNs) are often viewed as a model of biological object recognition, they lack many computational and architectural motifs that are postulated to contribute to robust perception in biological neural systems. For example, modern CNNs lack lateral connections, which greatly outnumber feed-forward excitatory connections in primary sensory cortical areas and mediate feature-specific competition between neighboring neurons to form robust,...
Show moreAlthough state-of-the-art Convolutional Neural Networks (CNNs) are often viewed as a model of biological object recognition, they lack many computational and architectural motifs that are postulated to contribute to robust perception in biological neural systems. For example, modern CNNs lack lateral connections, which greatly outnumber feed-forward excitatory connections in primary sensory cortical areas and mediate feature-specific competition between neighboring neurons to form robust, sparse representations of sensory stimuli for downstream tasks. In this thesis, I hypothesize that CNN layers equipped with lateral competition better approximate the response characteristics and dynamics of neurons in the mammalian primary visual cortex, leading to increased robustness under noise and/or adversarial attacks relative to current robust CNN layers. To test this hypothesis, I develop a new class of CNNs called LCANets, which simulate recurrent, feature-specific lateral competition between neighboring neurons via a sparse coding model termed the Locally Competitive Algorithm (LCA). I first perform an analysis of the response properties of LCA and show that sparse representations formed by lateral competition more accurately mirror response characteristics of primary visual cortical populations and are more useful for downstream tasks like object recognition than previous sparse CNNs, which approximate competition with winner-take-all mechanisms implemented via thresholding.
Show less - Date Issued
- 2022
- PURL
- http://purl.flvc.org/fau/fd/FA00014050
- Subject Headings
- Neural networks (Computer science), Machine learning, Computer vision
- Format
- Document (PDF)
- Title
- DATA-DRIVEN IDENTIFICATION AND CONTROL OF TURBULENT STRUCTURES USING DEEP NEURAL NETWORKS.
- Creator
- Jagodinski, Eric, Verma, Siddhartha, Florida Atlantic University, Department of Ocean and Mechanical Engineering, College of Engineering and Computer Science
- Abstract/Description
-
Wall-bounded turbulent flows are pervasive in numerous physics and engineering applications. Such flows tend to have a strong impact on the design of ships, airplanes and rockets, industrial chemical mixing, wind and hydrokinetic energy, utility infrastructure and innumerable other fields. Understanding and controlling wall bounded turbulence has been a long-pursued endeavor yielding plentiful scientific and engineering discoveries, but there is much that remains unexplained from a...
Show moreWall-bounded turbulent flows are pervasive in numerous physics and engineering applications. Such flows tend to have a strong impact on the design of ships, airplanes and rockets, industrial chemical mixing, wind and hydrokinetic energy, utility infrastructure and innumerable other fields. Understanding and controlling wall bounded turbulence has been a long-pursued endeavor yielding plentiful scientific and engineering discoveries, but there is much that remains unexplained from a fundamental viewpoint. One unexplained phenomenon is the formation and impact of coherent structures like the ejections of slow near-wall fluid into faster moving ow which have been shown to correlate with increases in friction drag. This thesis focuses on recognizing and regulating organized structures within wall-bounded turbulent flows using a variety of machine learning techniques to overcome the nonlinear nature of this phenomenon. Deep Learning has provided new avenues of analyzing large amounts of data by applying techniques modeled after biological neurons. These techniques allow for the discovery of nonlinear relationships in massive, complex systems like the data found frequently in fluid dynamics simulation. Using a neural network architecture called Convolutional Neural Networks that specializes in uncovering spatial relationships, a network was trained to estimate the relative intensity of ejection structures within turbulent flow simulation without any a priori knowledge of the underlying flow dynamics. To explore the underlying physics that the trained network might reveal, an interpretation technique called Gradient-based Class Activation Mapping was modified to identify salient regions in the flow field which most influenced the trained network to make an accurate estimation of these organized structures. Using various statistical techniques, these salient regions were found to have a high correlation to ejection structures, and to high positive kinetic energy production, low negative production, and low energy dissipation regions within the flow. Additionally, these techniques present a general framework for identifying nonlinear causal structures in general three-dimensional data in any scientific domain where the underlying physics may be unknown.
Show less - Date Issued
- 2022
- PURL
- http://purl.flvc.org/fau/fd/FA00014119
- Subject Headings
- Turbulent flow, Turbulence, Neural networks (Computer science), Deep learning (Machine learning)
- Format
- Document (PDF)
- Title
- DEEP MAXOUT NETWORKS FOR CLASSIFICATION PROBLEMS ACROSS MULTIPLE DOMAINS.
- Creator
- Castaneda, Gabriel, Khoshgoftaar, Taghi M., Florida Atlantic University, Department of Computer and Electrical Engineering and Computer Science, College of Engineering and Computer Science
- Abstract/Description
-
Machine learning techniques such as deep neural networks have become an indispensable tool for a wide range of applications such as image classification, speech recognition, and sentiment analysis in text. An activation function is a mathematical equation that determines the output of each neuron in the neural network. In deep learning architectures the choice of activation functions is very important to the network’s performance. Activation functions determine the output of the model, its...
Show moreMachine learning techniques such as deep neural networks have become an indispensable tool for a wide range of applications such as image classification, speech recognition, and sentiment analysis in text. An activation function is a mathematical equation that determines the output of each neuron in the neural network. In deep learning architectures the choice of activation functions is very important to the network’s performance. Activation functions determine the output of the model, its computational efficiency, and its ability to train and converge after multiple iterations of training epochs. The selection of an activation function is critical to building and training an effective and efficient neural network. In real-world applications of deep neural networks, the activation function is a hyperparameter. We have observed a lack of consensus on how to select a good activation function for a deep neural network, and that a specific function may not be suitable for all domain-specific applications.
Show less - Date Issued
- 2019
- PURL
- http://purl.flvc.org/fau/fd/FA00013362
- Subject Headings
- Classification, Machine learning--Technique, Neural networks (Computer science)
- Format
- Document (PDF)
- Title
- Design of analog building blocks useful for artificial neural networks.
- Creator
- Renavikar, Ajit Anand., Florida Atlantic University, Shankar, Ravi, College of Engineering and Computer Science, Department of Computer and Electrical Engineering and Computer Science
- Abstract/Description
-
Software simulations of a scaleable VLSI implementable architecture and algorithm for character recognition by a research group at Florida Atlantic University (FAU) have shown encouraging results. We address here hardware implementation issues pertinent to the classification phase of character recognition. Using the digit classification techniques developed at FAU as a foundation, we have designed and simulated general purpose building blocks useful for a possible implementation of a Digital ...
Show moreSoftware simulations of a scaleable VLSI implementable architecture and algorithm for character recognition by a research group at Florida Atlantic University (FAU) have shown encouraging results. We address here hardware implementation issues pertinent to the classification phase of character recognition. Using the digit classification techniques developed at FAU as a foundation, we have designed and simulated general purpose building blocks useful for a possible implementation of a Digital & Analog CMOS VLSI chip that is suitable for a variety of artificial neural network (ANN) architectures. HSPICE was used to perform circuit-level simulations of the building blocks. We present here the details of implementation of the recognition chip including the architecture, circuit design and the simulation results.
Show less - Date Issued
- 1996
- PURL
- http://purl.flvc.org/fcla/dt/15328
- Subject Headings
- Neural networks (Computer science), Artificial intelligence, Optical character recognition devices, Pattern recognition systems
- Format
- Document (PDF)
- Title
- DETECTION AND CATEGORIZATION OF LUNG CANCER USING CONVOLUTIONAL NEURAL NETWORK.
- Creator
- Mostafanazhad, Shahabeddin Aslmarand, Muhammad, Wazir, Florida Atlantic University, Department of Physics, Charles E. Schmidt College of Science
- Abstract/Description
-
Medical professionals use CT images to get information about the size, shape, and location of any lung nodules. This information will help radiologist and oncologist to identify the type of cancer and create a treatment plan. However, most of the time, the diagnosis regarding the types of lung cancer is error-prone and time-consuming. One way to address these problems is by using convolutional neural networks. In this Thesis, we developed a convolutional neural network that can detect...
Show moreMedical professionals use CT images to get information about the size, shape, and location of any lung nodules. This information will help radiologist and oncologist to identify the type of cancer and create a treatment plan. However, most of the time, the diagnosis regarding the types of lung cancer is error-prone and time-consuming. One way to address these problems is by using convolutional neural networks. In this Thesis, we developed a convolutional neural network that can detect abnormalities in lung CT scans and further categorize the abnormalities to benign, malignant adenocarcinoma and malignant squamous cell carcinoma. Our network is based on DenseNet, which utilizes dense connections between layers (dense blocks), so that all layers are connected. Because of all layers being connected, different layers can reuse features from previous layers which speeds up the process and make this network computationally efficient. To retrain this network we used CT images for 314 patients (over 1500 CT images) consistent of 42 Lung Adenocarcinoma and 78 Squamous Cell Carcinoma, 118 Non cancer and 76 benign were acquired from the National Lung Screening Trial (NLST). These images were divided to two categories of Training and Validation with 70% being training dataset and 30% as validation dataset. We trained our network on Training dataset and then checked the accuracy of our model using the validation dataset. Our model was able to categorize lung cancer with an accuracy of 88%. Afterwards we calculated the the confusion matrix, Precision (Sensitivity), Recall (Positivity) and F1 score of our model for each category. Our model is able to classify Normal CT images with Normal Accuracy of 89% Precision of 94% and F1 score of 93%. For benign nodules Accuracy was 92% precision of 97% and F1 score 86%, while for Adenocarcinoma and squamous cell cancer the Accuracy was 98% and 93%, Precision 85% and 84% and F1 score 92% and 86.9%. The relatively high accuracy of our model shows that convolutional neural networks can be a valuable tool for the classification of lung cancer, especially in a small city or underdeveloped rural hospital settings and can play a role in achieving healthcare equality.
Show less - Date Issued
- 2022
- PURL
- http://purl.flvc.org/fau/fd/FA00013965
- Subject Headings
- Lungs--Cancer, Neural networks (Computer science), Tomography, X-Ray Computed
- Format
- Document (PDF)