Matching Items (5)
Filtering by
- All Subjects: Computer Engineering
- Genre: Masters Thesis
- Creators: Berisha, Visar
- Member of: Theses and Dissertations
- Resource Type: Text
- Status: Published
Description
As the number of devices with wireless capabilities and the proximity of these devices to each other increases, better ways to handle the interference they cause need to be explored. Also important is for these devices to keep up with the demand for data rates while not compromising on industry established expectations of power consumption and mobility. Current methods of distributing the spectrum among all participants are expected to not cope with the demand in a very near future. In this thesis, the effect of employing sophisticated multiple-input, multiple-output (MIMO) systems in this regard is explored. The efficacy of systems which can make intelligent decisions on the transmission mode usage and power allocation to these modes becomes relevant in the current scenario, where the need for performance far exceeds the cost expendable on hardware. The effect of adding multiple antennas at either ends will be examined, the capacity of such systems and of networks comprised of many such participants will be evaluated. Methods of simulating said networks, and ways to achieve better performance by making intelligent transmission decisions will be proposed. Finally, a way of access control closer to the physical layer (a 'statistical MAC') and a possible metric to be used for such a MAC is suggested.
ContributorsThontadarya, Niranjan (Author) / Bliss, Daniel W (Thesis advisor) / Berisha, Visar (Committee member) / Ying, Lei (Committee member) / Arizona State University (Publisher)
Created2014
Description
Deep neural networks (DNN) have shown tremendous success in various cognitive tasks, such as image classification, speech recognition, etc. However, their usage on resource-constrained edge devices has been limited due to high computation and large memory requirement.
To overcome these challenges, recent works have extensively investigated model compression techniques such as element-wise sparsity, structured sparsity and quantization. While most of these works have applied these compression techniques in isolation, there have been very few studies on application of quantization and structured sparsity together on a DNN model.
This thesis co-optimizes structured sparsity and quantization constraints on DNN models during training. Specifically, it obtains optimal setting of 2-bit weight and 2-bit activation coupled with 4X structured compression by performing combined exploration of quantization and structured compression settings. The optimal DNN model achieves 50X weight memory reduction compared to floating-point uncompressed DNN. This memory saving is significant since applying only structured sparsity constraints achieves 2X memory savings and only quantization constraints achieves 16X memory savings. The algorithm has been validated on both high and low capacity DNNs and on wide-sparse and deep-sparse DNN models. Experiments demonstrated that deep-sparse DNN outperforms shallow-dense DNN with varying level of memory savings depending on DNN precision and sparsity levels. This work further proposed a Pareto-optimal approach to systematically extract optimal DNN models from a huge set of sparse and dense DNN models. The resulting 11 optimal designs were further evaluated by considering overall DNN memory which includes activation memory and weight memory. It was found that there is only a small change in the memory footprint of the optimal designs corresponding to the low sparsity DNNs. However, activation memory cannot be ignored for high sparsity DNNs.
To overcome these challenges, recent works have extensively investigated model compression techniques such as element-wise sparsity, structured sparsity and quantization. While most of these works have applied these compression techniques in isolation, there have been very few studies on application of quantization and structured sparsity together on a DNN model.
This thesis co-optimizes structured sparsity and quantization constraints on DNN models during training. Specifically, it obtains optimal setting of 2-bit weight and 2-bit activation coupled with 4X structured compression by performing combined exploration of quantization and structured compression settings. The optimal DNN model achieves 50X weight memory reduction compared to floating-point uncompressed DNN. This memory saving is significant since applying only structured sparsity constraints achieves 2X memory savings and only quantization constraints achieves 16X memory savings. The algorithm has been validated on both high and low capacity DNNs and on wide-sparse and deep-sparse DNN models. Experiments demonstrated that deep-sparse DNN outperforms shallow-dense DNN with varying level of memory savings depending on DNN precision and sparsity levels. This work further proposed a Pareto-optimal approach to systematically extract optimal DNN models from a huge set of sparse and dense DNN models. The resulting 11 optimal designs were further evaluated by considering overall DNN memory which includes activation memory and weight memory. It was found that there is only a small change in the memory footprint of the optimal designs corresponding to the low sparsity DNNs. However, activation memory cannot be ignored for high sparsity DNNs.
ContributorsSrivastava, Gaurav (Author) / Seo, Jae-Sun (Thesis advisor) / Chakrabarti, Chaitali (Committee member) / Berisha, Visar (Committee member) / Arizona State University (Publisher)
Created2018
Description
Many neurological disorders, especially those that result in dementia, impact speech and language production. A number of studies have shown that there exist subtle changes in linguistic complexity in these individuals that precede disease onset. However, these studies are conducted on controlled speech samples from a specific task. This thesis explores the possibility of using natural language processing in order to detect declining linguistic complexity from more natural discourse. We use existing data from public figures suspected (or at risk) of suffering from cognitive-linguistic decline, downloaded from the Internet, to detect changes in linguistic complexity. In particular, we focus on two case studies. The first case study analyzes President Ronald Reagan’s transcribed spontaneous speech samples during his presidency. President Reagan was diagnosed with Alzheimer’s disease in 1994, however my results showed declining linguistic complexity during the span of the 8 years he was in office. President George Herbert Walker Bush, who has no known diagnosis of Alzheimer’s disease, shows no decline in the same measures. In the second case study, we analyze transcribed spontaneous speech samples from the news conferences of 10 current NFL players and 18 non-player personnel since 2007. The non-player personnel have never played professional football. Longitudinal analysis of linguistic complexity showed contrasting patterns in the two groups. The majority (6 of 10) of current players showed decline in at least one measure of linguistic complexity over time. In contrast, the majority (11 out of 18) of non-player personnel showed an increase in at least one linguistic complexity measure.
ContributorsWang, Shuai (Author) / Berisha, Visar (Thesis advisor) / LaCross, Amy (Committee member) / Tong, Hanghang (Committee member) / Arizona State University (Publisher)
Created2016
Description
Deep neural networks (DNNs) have had tremendous success in a variety of
statistical learning applications due to their vast expressive power. Most
applications run DNNs on the cloud on parallelized architectures. There is a need
for for efficient DNN inference on edge with low precision hardware and analog
accelerators. To make trained models more robust for this setting, quantization and
analog compute noise are modeled as weight space perturbations to DNNs and an
information theoretic regularization scheme is used to penalize the KL-divergence
between perturbed and unperturbed models. This regularizer has similarities to
both natural gradient descent and knowledge distillation, but has the advantage of
explicitly promoting the network to and a broader minimum that is robust to
weight space perturbations. In addition to the proposed regularization,
KL-divergence is directly minimized using knowledge distillation. Initial validation
on FashionMNIST and CIFAR10 shows that the information theoretic regularizer
and knowledge distillation outperform existing quantization schemes based on the
straight through estimator or L2 constrained quantization.
statistical learning applications due to their vast expressive power. Most
applications run DNNs on the cloud on parallelized architectures. There is a need
for for efficient DNN inference on edge with low precision hardware and analog
accelerators. To make trained models more robust for this setting, quantization and
analog compute noise are modeled as weight space perturbations to DNNs and an
information theoretic regularization scheme is used to penalize the KL-divergence
between perturbed and unperturbed models. This regularizer has similarities to
both natural gradient descent and knowledge distillation, but has the advantage of
explicitly promoting the network to and a broader minimum that is robust to
weight space perturbations. In addition to the proposed regularization,
KL-divergence is directly minimized using knowledge distillation. Initial validation
on FashionMNIST and CIFAR10 shows that the information theoretic regularizer
and knowledge distillation outperform existing quantization schemes based on the
straight through estimator or L2 constrained quantization.
ContributorsKadambi, Pradyumna (Author) / Berisha, Visar (Thesis advisor) / Dasarathy, Gautam (Committee member) / Seo, Jae-Sun (Committee member) / Cao, Yu (Committee member) / Arizona State University (Publisher)
Created2019
Description
Speech is known to serve as an early indicator of neurological decline, particularly in motor diseases. There is significant interest in developing automated, objective signal analytics that detect clinically-relevant changes and in evaluating these algorithms against the existing gold-standard: perceptual evaluation by trained speech and language pathologists. Hypernasality, the result of poor control of the velopharyngeal flap---the soft palate regulating airflow between the oral and nasal cavities---is one such speech symptom of interest, as precise velopharyngeal control is difficult to achieve under neuromuscular disorders. However, a host of co-modulating variables give hypernasal speech a complex and highly variable acoustic signature, making it difficult for skilled clinicians to assess and for automated systems to evaluate. Previous work in rating hypernasality from speech relies on either engineered features based on statistical signal processing or machine learning models trained end-to-end on clinical ratings of disordered speech examples. Engineered features often fail to capture the complex acoustic patterns associated with hypernasality, while end-to-end methods tend to overfit to the small datasets on which they are trained. In this thesis, I present a set of acoustic features, models, and strategies for characterizing hypernasality in dysarthric speech that split the difference between these two approaches, with the aim of capturing the complex perceptual character of hypernasality without overfitting to the small datasets available. The features are based on acoustic models trained on a large corpus of healthy speech, integrating expert knowledge to capture known perceptual characteristics of hypernasal speech. They are then used in relatively simple linear models to predict clinician hypernasality scores. These simple models are robust, generalizing across diseases and outperforming comprehensive set of baselines in accuracy and correlation. This novel approach represents a new state-of-the-art in objective hypernasality assessment.
ContributorsSaxon, Michael Stephen (Author) / Berisha, Visar (Thesis advisor) / Panchanathan, Sethuraman (Thesis advisor) / Venkateswara, Hemanth (Committee member) / Arizona State University (Publisher)
Created2020