Matching Items (15)
Filtering by
- All Subjects: Machine Learning
- Creators: Papandreou-Suppappola, Antonia
- Member of: ASU Electronic Theses and Dissertations
Description
The advancement and marked increase in the use of computing devices in health care for large scale and personal medical use has transformed the field of medicine and health care into a data rich domain. This surge in the availability of data has allowed domain experts to investigate, study and discover inherent patterns in diseases from new perspectives and in turn, further the field of medicine. Storage and analysis of this data in real time aids in enhancing the response time and efficiency of doctors and health care specialists. However, due to the time critical nature of most life- threatening diseases, there is a growing need to make informed decisions prior to the occurrence of any fatal outcome. Alongside time sensitivity, analyzing data specific to diseases and their effects on an individual basis leads to more efficient prognosis and rapid deployment of cures. The primary challenge in addressing both of these issues arises from the time varying and time sensitive nature of the data being studied and in the ability to successfully predict anomalous events using only observed data.This dissertation introduces adaptive machine learning algorithms that aid in the prediction of anomalous situations arising due to abnormalities present in patients diagnosed with certain types of diseases. Emphasis is given to the adaptation and development of algorithms based on an individual basis to further the accuracy of all predictions made. The main objectives are to learn the underlying representation of the data using empirical methods and enhance it using domain knowledge. The learned model is then utilized as a guide for statistical machine learning methods to predict the occurrence of anomalous events in the near future. Further enhancement of the learned model is achieved by means of tuning the objective function of the algorithm to incorporate domain knowledge. Along with anomaly forecasting using multi-modal data, this dissertation also investigates the use of univariate time series data towards the prediction of onset of diseases using Bayesian nonparametrics.
ContributorsDas, Subhasish (Author) / Gupta, Sandeep K.S. (Thesis advisor) / Banerjee, Ayan (Committee member) / Indic, Premananda (Committee member) / Papandreou-Suppappola, Antonia (Committee member) / Arizona State University (Publisher)
Created2022
Description
Multi-segment manipulators and mobile robot collectives are examples of multi-agent robotic systems, in which each segment or robot can be considered an agent. Fundamental motion control problems for such systems include the stabilization of one or more agents to target configurations or trajectories while preventing inter-agent collisions, agent collisions with obstacles, and deadlocks. Despite extensive research on these control problems, there are still challenges in designing controllers that (1) are scalable with the number of agents; (2) have theoretical guarantees on collision-free agent navigation; and (3) can be used when the states of the agents and the environment are only partially observable. Existing centralized and distributed control architectures have limited scalability due to their computational complexity and communication requirements, while decentralized control architectures are often effective only under impractical assumptions that do not hold in real-world implementations. The main objective of this dissertation is to develop and evaluate decentralized approaches for multi-agent motion control that enable agents to use their onboard sensors and computational resources to decide how to move through their environment, with limited or absent inter-agent communication and external supervision. Specifically, control approaches are designed for multi-segment manipulators and mobile robot collectives to achieve position and pose (position and orientation) stabilization, trajectory tracking, and collision and deadlock avoidance. These control approaches are validated in both simulations and physical experiments to show that they can be implemented in real-time while remaining computationally tractable. First, kinematic controllers are proposed for position stabilization and trajectory tracking control of two- or three-dimensional hyper-redundant multi-segment manipulators. Next, robust and gradient-based feedback controllers are presented for individual holonomic and nonholonomic mobile robots that achieve position stabilization, trajectory tracking control, and obstacle avoidance. Then, nonlinear Model Predictive Control methods are developed for collision-free, deadlock-free pose stabilization and trajectory tracking control of multiple nonholonomic mobile robots in known and unknown environments with obstacles, both static and dynamic. Finally, a feedforward proportional-derivative controller is defined for collision-free velocity tracking of a moving ground target by multiple unmanned aerial vehicles.
ContributorsSalimi Lafmejani, Amir (Author) / Berman, Spring (Thesis advisor) / Tsakalis, Konstantinos (Thesis advisor) / Papandreou-Suppappola, Antonia (Committee member) / Marvi, Hamidreza (Committee member) / Arizona State University (Publisher)
Created2022
Description
Predicting nonlinear dynamical systems has been a long-standing challenge in science. This field is currently witnessing a revolution with the advent of machine learning methods. Concurrently, the analysis of dynamics in various nonlinear complex systems continues to be crucial. Guided by these directions, I conduct the following studies. Predicting critical transitions and transient states in nonlinear dynamics is a complex problem. I developed a solution called parameter-aware reservoir computing, which uses machine learning to track how system dynamics change with a driving parameter. I show that the transition point can be accurately predicted while trained in a sustained functioning regime before the transition. Notably, it can also predict if the system will enter a transient state, the distribution of transient lifetimes, and their average before a final collapse, which are crucial for management. I introduce a machine-learning-based digital twin for monitoring and predicting the evolution of externally driven nonlinear dynamical systems, where reservoir computing is exploited. Extensive tests on various models, encompassing optics, ecology, and climate, verify the approach’s effectiveness. The digital twins can extrapolate unknown system dynamics, continually forecast and monitor under non-stationary external driving, infer hidden variables, adapt to different driving waveforms, and extrapolate bifurcation behaviors across varying system sizes. Integrating engineered gene circuits into host cells poses a significant challenge in synthetic biology due to circuit-host interactions, such as growth feedback. I conducted systematic studies on hundreds of circuit structures exhibiting various functionalities, and identified a comprehensive categorization of growth-induced failures. I discerned three dynamical mechanisms behind these circuit failures. Moreover, my comprehensive computations reveal a scaling law between the circuit robustness and the intensity of growth feedback. A class of circuits with optimal robustness is also identified. Chimera states, a phenomenon of symmetry-breaking in oscillator networks, traditionally have transient lifetimes that grow exponentially with system size. However, my research on high-dimensional oscillators leads to the discovery of ’short-lived’ chimera states. Their lifetime increases logarithmically with system size and decreases logarithmically with random perturbations, indicating a unique fragility. To understand these states, I use a transverse stability analysis supported by simulations.
ContributorsKong, Lingwei (Author) / Lai, Ying-Cheng (Thesis advisor) / Tian, Xiaojun (Committee member) / Papandreou-Suppappola, Antonia (Committee member) / Alkhateeb, Ahmed (Committee member) / Arizona State University (Publisher)
Created2023
Description
Disentangling latent spaces is an important research direction in the interpretability of unsupervised machine learning. Several recent works using deep learning are very effective at producing disentangled representations. However, in the unsupervised setting, there is no way to pre-specify which part of the latent space captures specific factors of variations. While this is generally a hard problem because of the non-existence of analytical expressions to capture these variations, there are certain factors like geometric
transforms that can be expressed analytically. Furthermore, in existing frameworks, the disentangled values are also not interpretable. The focus of this work is to disentangle these geometric factors of variations (which turn out to be nuisance factors for many applications) from the semantic content of the signal in an interpretable manner which in turn makes the features more discriminative. Experiments are designed to show the modularity of the approach with other disentangling strategies as well as on multiple one-dimensional (1D) and two-dimensional (2D) datasets, clearly indicating the efficacy of the proposed approach.
transforms that can be expressed analytically. Furthermore, in existing frameworks, the disentangled values are also not interpretable. The focus of this work is to disentangle these geometric factors of variations (which turn out to be nuisance factors for many applications) from the semantic content of the signal in an interpretable manner which in turn makes the features more discriminative. Experiments are designed to show the modularity of the approach with other disentangling strategies as well as on multiple one-dimensional (1D) and two-dimensional (2D) datasets, clearly indicating the efficacy of the proposed approach.
ContributorsKoneripalli Seetharam, Kaushik (Author) / Turaga, Pavan (Thesis advisor) / Papandreou-Suppappola, Antonia (Committee member) / Jayasuriya, Suren (Committee member) / Arizona State University (Publisher)
Created2019
Description
Deep learning (DL) has proved itself be one of the most important developements till date with far reaching impacts in numerous fields like robotics, computer vision, surveillance, speech processing, machine translation, finance, etc. They are now widely used for countless applications because of their ability to generalize real world data, robustness to noise in previously unseen data and high inference accuracy. With the ability to learn useful features from raw sensor data, deep learning algorithms have out-performed tradinal AI algorithms and pushed the boundaries of what can be achieved with AI. In this work, we demonstrate the power of deep learning by developing a neural network to automatically detect cough instances from audio recorded in un-constrained environments. For this, 24 hours long recordings from 9 dierent patients is collected and carefully labeled by medical personel. A pre-processing algorithm is proposed to convert event based cough dataset to a more informative dataset with start and end of coughs and also introduce data augmentation for regularizing the training procedure. The proposed neural network achieves 92.3% leave-one-out accuracy on data captured in real world.
Deep neural networks are composed of multiple layers that are compute/memory intensive. This makes it difficult to execute these algorithms real-time with low power consumption using existing general purpose computers. In this work, we propose hardware accelerators for a traditional AI algorithm based on random forest trees and two representative deep convolutional neural networks (AlexNet and VGG). With the proposed acceleration techniques, ~ 30x performance improvement was achieved compared to CPU for random forest trees. For deep CNNS, we demonstrate that much higher performance can be achieved with architecture space exploration using any optimization algorithms with system level performance and area models for hardware primitives as inputs and goal of minimizing latency with given resource constraints. With this method, ~30GOPs performance was achieved for Stratix V FPGA boards.
Hardware acceleration of DL algorithms alone is not always the most ecient way and sucient to achieve desired performance. There is a huge headroom available for performance improvement provided the algorithms are designed keeping in mind the hardware limitations and bottlenecks. This work achieves hardware-software co-optimization for Non-Maximal Suppression (NMS) algorithm. Using the proposed algorithmic changes and hardware architecture
With CMOS scaling coming to an end and increasing memory bandwidth bottlenecks, CMOS based system might not scale enough to accommodate requirements of more complicated and deeper neural networks in future. In this work, we explore RRAM crossbars and arrays as compact, high performing and energy efficient alternative to CMOS accelerators for deep learning training and inference. We propose and implement RRAM periphery read and write circuits and achieved ~3000x performance improvement in online dictionary learning compared to CPU.
This work also examines the realistic RRAM devices and their non-idealities. We do an in-depth study of the effects of RRAM non-idealities on inference accuracy when a pretrained model is mapped to RRAM based accelerators. To mitigate this issue, we propose Random Sparse Adaptation (RSA), a novel scheme aimed at tuning the model to take care of the faults of the RRAM array on which it is mapped. Our proposed method can achieve inference accuracy much higher than what traditional Read-Verify-Write (R-V-W) method could achieve. RSA can also recover lost inference accuracy 100x ~ 1000x faster compared to R-V-W. Using 32-bit high precision RSA cells, we achieved ~10% higher accuracy using fautly RRAM arrays compared to what can be achieved by mapping a deep network to an 32 level RRAM array with no variations.
Deep neural networks are composed of multiple layers that are compute/memory intensive. This makes it difficult to execute these algorithms real-time with low power consumption using existing general purpose computers. In this work, we propose hardware accelerators for a traditional AI algorithm based on random forest trees and two representative deep convolutional neural networks (AlexNet and VGG). With the proposed acceleration techniques, ~ 30x performance improvement was achieved compared to CPU for random forest trees. For deep CNNS, we demonstrate that much higher performance can be achieved with architecture space exploration using any optimization algorithms with system level performance and area models for hardware primitives as inputs and goal of minimizing latency with given resource constraints. With this method, ~30GOPs performance was achieved for Stratix V FPGA boards.
Hardware acceleration of DL algorithms alone is not always the most ecient way and sucient to achieve desired performance. There is a huge headroom available for performance improvement provided the algorithms are designed keeping in mind the hardware limitations and bottlenecks. This work achieves hardware-software co-optimization for Non-Maximal Suppression (NMS) algorithm. Using the proposed algorithmic changes and hardware architecture
With CMOS scaling coming to an end and increasing memory bandwidth bottlenecks, CMOS based system might not scale enough to accommodate requirements of more complicated and deeper neural networks in future. In this work, we explore RRAM crossbars and arrays as compact, high performing and energy efficient alternative to CMOS accelerators for deep learning training and inference. We propose and implement RRAM periphery read and write circuits and achieved ~3000x performance improvement in online dictionary learning compared to CPU.
This work also examines the realistic RRAM devices and their non-idealities. We do an in-depth study of the effects of RRAM non-idealities on inference accuracy when a pretrained model is mapped to RRAM based accelerators. To mitigate this issue, we propose Random Sparse Adaptation (RSA), a novel scheme aimed at tuning the model to take care of the faults of the RRAM array on which it is mapped. Our proposed method can achieve inference accuracy much higher than what traditional Read-Verify-Write (R-V-W) method could achieve. RSA can also recover lost inference accuracy 100x ~ 1000x faster compared to R-V-W. Using 32-bit high precision RSA cells, we achieved ~10% higher accuracy using fautly RRAM arrays compared to what can be achieved by mapping a deep network to an 32 level RRAM array with no variations.
ContributorsMohanty, Abinash (Author) / Cao, Yu (Thesis advisor) / Seo, Jae-Sun (Committee member) / Vrudhula, Sarma (Committee member) / Chakrabarti, Chaitali (Committee member) / Arizona State University (Publisher)
Created2018
Description
This dissertation presents the development of structural health monitoring and prognostic health management methodologies for complex structures and systems in the field of mechanical engineering. To overcome various challenges historically associated with complex structures and systems such as complicated sensing mechanisms, noisy information, and large-size datasets, a hybrid monitoring framework comprising of solid mechanics concepts and data mining technologies is developed. In such a framework, the solid mechanics simulations provide additional intuitions to data mining techniques reducing the dependence of accuracy on the training set, while the data mining approaches fuse and interpret information from the targeted system enabling the capability for real-time monitoring with efficient computation.
In the case of structural health monitoring, ultrasonic guided waves are utilized for damage identification and localization in complex composite structures. Signal processing and data mining techniques are integrated into the damage localization framework, and the converted wave modes, which are induced by the thickness variation due to the presence of delamination, are used as damage indicators. This framework has been validated through experiments and has shown sufficient accuracy in locating delamination in X-COR sandwich composites without the need of baseline information. Besides the localization of internal damage, the Gaussian process machine learning technique is integrated with finite element method as an online-offline prediction model to predict crack propagation with overloads under biaxial loading conditions; such a probabilistic prognosis model, with limited number of training examples, has shown increased accuracy over state-of-the-art techniques in predicting crack retardation behaviors induced by overloads. In the case of system level management, a monitoring framework built using a multivariate Gaussian model as basis is developed to evaluate the anomalous condition of commercial aircrafts. This method has been validated using commercial airline data and has shown high sensitivity to variations in aircraft dynamics and pilot operations. Moreover, this framework was also tested on simulated aircraft faults and its feasibility for real-time monitoring was demonstrated with sufficient computation efficiency.
This research is expected to serve as a practical addition to the existing literature while possessing the potential to be adopted in realistic engineering applications.
In the case of structural health monitoring, ultrasonic guided waves are utilized for damage identification and localization in complex composite structures. Signal processing and data mining techniques are integrated into the damage localization framework, and the converted wave modes, which are induced by the thickness variation due to the presence of delamination, are used as damage indicators. This framework has been validated through experiments and has shown sufficient accuracy in locating delamination in X-COR sandwich composites without the need of baseline information. Besides the localization of internal damage, the Gaussian process machine learning technique is integrated with finite element method as an online-offline prediction model to predict crack propagation with overloads under biaxial loading conditions; such a probabilistic prognosis model, with limited number of training examples, has shown increased accuracy over state-of-the-art techniques in predicting crack retardation behaviors induced by overloads. In the case of system level management, a monitoring framework built using a multivariate Gaussian model as basis is developed to evaluate the anomalous condition of commercial aircrafts. This method has been validated using commercial airline data and has shown high sensitivity to variations in aircraft dynamics and pilot operations. Moreover, this framework was also tested on simulated aircraft faults and its feasibility for real-time monitoring was demonstrated with sufficient computation efficiency.
This research is expected to serve as a practical addition to the existing literature while possessing the potential to be adopted in realistic engineering applications.
ContributorsLi, Guoyi (Ph.D.) (Author) / Chattopadhyay, Aditi (Thesis advisor) / Mignolet, Marc (Committee member) / Papandreou-Suppappola, Antonia (Committee member) / Yekani Fard, Masoud (Committee member) / Jiang, Hanqing (Committee member) / Arizona State University (Publisher)
Created2019
Description
Biological and biomedical measurements, when adequately analyzed and processed, can be used to impart quantitative diagnosis during primary health care consultation to improve patient adherence to recommended treatments. For example, analyzing neural recordings from neurostimulators implanted in patients with neurological disorders can be used by a physician to adjust detrimental stimulation parameters to improve treatment. As another example, biosequences, such as sequences from peptide microarrays obtained from a biological sample, can potentially provide pre-symptomatic diagnosis for infectious diseases when processed to associate antibodies to specific pathogens or infectious agents. This work proposes advanced statistical signal processing and machine learning methodologies to assess neurostimulation from neural recordings and to extract diagnostic information from biosequences.
For locating specific cognitive and behavioral information in different regions of the brain, neural recordings are processed using sequential Bayesian filtering methods to detect and estimate both the number of neural sources and their corresponding parameters. Time-frequency based feature selection algorithms are combined with adaptive machine learning approaches to suppress physiological and non-physiological artifacts present in neural recordings. Adaptive processing and unsupervised clustering methods applied to neural recordings are also used to suppress neurostimulation artifacts and classify between various behavior tasks to assess the level of neurostimulation in patients.
For pathogen detection and identification, random peptide sequences and their properties are first uniquely mapped to highly-localized signals and their corresponding parameters in the time-frequency plane. Time-frequency signal processing methods are then applied to estimate antigenic determinants or epitope candidates for detecting and identifying potential pathogens.
For locating specific cognitive and behavioral information in different regions of the brain, neural recordings are processed using sequential Bayesian filtering methods to detect and estimate both the number of neural sources and their corresponding parameters. Time-frequency based feature selection algorithms are combined with adaptive machine learning approaches to suppress physiological and non-physiological artifacts present in neural recordings. Adaptive processing and unsupervised clustering methods applied to neural recordings are also used to suppress neurostimulation artifacts and classify between various behavior tasks to assess the level of neurostimulation in patients.
For pathogen detection and identification, random peptide sequences and their properties are first uniquely mapped to highly-localized signals and their corresponding parameters in the time-frequency plane. Time-frequency signal processing methods are then applied to estimate antigenic determinants or epitope candidates for detecting and identifying potential pathogens.
ContributorsMaurer, Alexander Joseph (Author) / Papandreou-Suppappola, Antonia (Thesis advisor) / Bliss, Daniel (Committee member) / Chakrabarti, Chaitali (Committee member) / Kovvali, Narayan (Committee member) / Arizona State University (Publisher)
Created2016
Description
The healthcare system in this country is currently unacceptable. New technologies may contribute to reducing cost and improving outcomes. Early diagnosis and treatment represents the least risky option for addressing this issue. Such a technology needs to be inexpensive, highly sensitive, highly specific, and amenable to adoption in a clinic. This thesis explores an immunodiagnostic technology based on highly scalable, non-natural sequence peptide microarrays designed to profile the humoral immune response and address the healthcare problem. The primary aim of this thesis is to explore the ability of these arrays to map continuous (linear) epitopes. I discovered that using a technique termed subsequence analysis where epitopes could be decisively mapped to an eliciting protein with high success rate. This led to the discovery of novel linear epitopes from Plasmodium falciparum (Malaria) and Treponema palladium (Syphilis), as well as validation of previously discovered epitopes in Dengue and monoclonal antibodies. Next, I developed and tested a classification scheme based on Support Vector Machines for development of a Dengue Fever diagnostic, achieving higher sensitivity and specificity than current FDA approved techniques. The software underlying this method is available for download under the BSD license. Following this, I developed a kinetic model for immunosignatures and tested it against existing data driven by previously unexplained phenomena. This model provides a framework and informs ways to optimize the platform for maximum stability and efficiency. I also explored the role of sequence composition in explaining an immunosignature binding profile, determining a strong role for charged residues that seems to have some predictive ability for disease. Finally, I developed a database, software and indexing strategy based on Apache Lucene for searching motif patterns (regular expressions) in large biological databases. These projects as a whole have advanced knowledge of how to approach high throughput immunodiagnostics and provide an example of how technology can be fused with biology in order to affect scientific and health outcomes.
ContributorsRicher, Joshua Amos (Author) / Johnston, Stephen A. (Thesis advisor) / Woodbury, Neal (Committee member) / Stafford, Phillip (Committee member) / Papandreou-Suppappola, Antonia (Committee member) / Arizona State University (Publisher)
Created2014
Description
The radar performance of detecting a target and estimating its parameters can deteriorate rapidly in the presence of high clutter. This is because radar measurements due to clutter returns can be falsely detected as if originating from the actual target. Various data association methods and multiple hypothesis filtering approaches have been considered to solve this problem. Such methods, however, can be computationally intensive for real time radar processing. This work proposes a new approach that is based on the unsupervised clustering of target and clutter detections before target tracking using particle filtering. In particular, Gaussian mixture modeling is first used to separate detections into two Gaussian distinct mixtures. Using eigenvector analysis, the eccentricity of the covariance matrices of the Gaussian mixtures are computed and compared to threshold values that are obtained a priori. The thresholding allows only target detections to be used for target tracking. Simulations demonstrate the performance of the new algorithm and compare it with using k-means for clustering instead of Gaussian mixture modeling.
ContributorsFreeman, Matthew Gregory (Author) / Papandreou-Suppappola, Antonia (Thesis advisor) / Bliss, Daniel (Thesis advisor) / Chakrabarti, Chaitali (Committee member) / Arizona State University (Publisher)
Created2016
Description
Machine learning technology has made a lot of incredible achievements in recent years. It has rivalled or exceeded human performance in many intellectual tasks including image recognition, face detection and the Go game. Many machine learning algorithms require huge amount of computation such as in multiplication of large matrices. As silicon technology has scaled to sub-14nm regime, simply scaling down the device cannot provide enough speed-up any more. New device technologies and system architectures are needed to improve the computing capacity. Designing specific hardware for machine learning is highly in demand. Efforts need to be made on a joint design and optimization of both hardware and algorithm.
For machine learning acceleration, traditional SRAM and DRAM based system suffer from low capacity, high latency, and high standby power. Instead, emerging memories, such as Phase Change Random Access Memory (PRAM), Spin-Transfer Torque Magnetic Random Access Memory (STT-MRAM), and Resistive Random Access Memory (RRAM), are promising candidates providing low standby power, high data density, fast access and excellent scalability. This dissertation proposes a hierarchical memory modeling framework and models PRAM and STT-MRAM in four different levels of abstraction. With the proposed models, various simulations are conducted to investigate the performance, optimization, variability, reliability, and scalability.
Emerging memory devices such as RRAM can work as a 2-D crosspoint array to speed up the multiplication and accumulation in machine learning algorithms. This dissertation proposes a new parallel programming scheme to achieve in-memory learning with RRAM crosspoint array. The programming circuitry is designed and simulated in TSMC 65nm technology showing 900X speedup for the dictionary learning task compared to the CPU performance.
From the algorithm perspective, inspired by the high accuracy and low power of the brain, this dissertation proposes a bio-plausible feedforward inhibition spiking neural network with Spike-Rate-Dependent-Plasticity (SRDP) learning rule. It achieves more than 95% accuracy on the MNIST dataset, which is comparable to the sparse coding algorithm, but requires far fewer number of computations. The role of inhibition in this network is systematically studied and shown to improve the hardware efficiency in learning.
For machine learning acceleration, traditional SRAM and DRAM based system suffer from low capacity, high latency, and high standby power. Instead, emerging memories, such as Phase Change Random Access Memory (PRAM), Spin-Transfer Torque Magnetic Random Access Memory (STT-MRAM), and Resistive Random Access Memory (RRAM), are promising candidates providing low standby power, high data density, fast access and excellent scalability. This dissertation proposes a hierarchical memory modeling framework and models PRAM and STT-MRAM in four different levels of abstraction. With the proposed models, various simulations are conducted to investigate the performance, optimization, variability, reliability, and scalability.
Emerging memory devices such as RRAM can work as a 2-D crosspoint array to speed up the multiplication and accumulation in machine learning algorithms. This dissertation proposes a new parallel programming scheme to achieve in-memory learning with RRAM crosspoint array. The programming circuitry is designed and simulated in TSMC 65nm technology showing 900X speedup for the dictionary learning task compared to the CPU performance.
From the algorithm perspective, inspired by the high accuracy and low power of the brain, this dissertation proposes a bio-plausible feedforward inhibition spiking neural network with Spike-Rate-Dependent-Plasticity (SRDP) learning rule. It achieves more than 95% accuracy on the MNIST dataset, which is comparable to the sparse coding algorithm, but requires far fewer number of computations. The role of inhibition in this network is systematically studied and shown to improve the hardware efficiency in learning.
ContributorsXu, Zihan (Author) / Cao, Yu (Thesis advisor) / Chakrabarti, Chaitali (Committee member) / Seo, Jae-Sun (Committee member) / Yu, Shimeng (Committee member) / Arizona State University (Publisher)
Created2017