Engineering Commons^™

Controllable Language Generation Using Deep Learning, Rohola Zandie

Electronic Theses and Dissertations

The advent of deep neural networks has sparked a revolution in Artificial Intelligence (AI), notably with the creation of Transformer models like GPT-X and ChatGPT. These models have surpassed previous methods in various Natural Language Processing (NLP) tasks. As the NLP field evolves, there is a need to further understand and question the capabilities of these models. Text generation, a crucial part of NLP, remains an area where our comprehension is limited while being critical in research.

This dissertation focuses on the challenging problem of controlling the general behaviors of language models such as sentiment, topical focus, and logical reasoning. …

Integrating The Spatial Pyramid Pooling Into 3d Convolutional Neural Networks For Cerebral Microbleeds Detection, Andre Accioly Veira

CCE Theses and Dissertations

Cerebral microbleeds (CMB) are small foci of chronic blood products in brain tissues that are critical markers for cerebral amyloid angiopathy. CMB increases the risk of symptomatic intracerebral hemorrhage and ischemic stroke. CMB can also cause structural damage to brain tissues resulting in neurologic dysfunction, cognitive impairment, and dementia. Due to the paramagnetic properties of blood degradation products, CMB can be better visualized via susceptibility-weighted imaging (SWI) than magnetic resonance imaging (MRI).CMB identification and classification have been based mainly on human visual identification of SWI features via shape, size, and intensity information. However, manual interpretation can be biased. Visual screening …

Ai-Based Traffic Forecasting In 5g Network, Maryam Mohseni

Electronic Thesis and Dissertation Repository

Forecasting of the telecommunication traffic is the foundation for enabling intelligent management features as cellular technologies evolve toward fifth-generation (5G) technology. Since a significant number of network slices are deployed over a 5G network, it is crucial to evaluate the resource requirements of each network slice and how they evolve over time. Mobile network carriers should investigate strategies for network optimization and resource allocation due to the steadily increasing mobile traffic. Network management and optimization strategies will be improved if mobile operators know the cellular traffic demand at a specific time and location beforehand. The most effective techniques nowadays devote …

Mathematical Optimization Algorithms For Model Compression And Adversarial Learning In Deep Neural Networks, Tianyun Zhang

Dissertations - ALL

Large-scale deep neural networks (DNNs) have made breakthroughs in a variety of tasks, such as image recognition, speech recognition and self-driving cars. However, their large model size and computational requirements add a significant burden to state-of-the-art computing systems. Weight pruning is an effective approach to reduce the model size and computational requirements of DNNs. However, prior works in this area are mainly heuristic methods. As a result, the performance of a DNN cannot maintain for a high weight pruning ratio. To mitigate this limitation, we propose a systematic weight pruning framework for DNNs based on mathematical optimization. We first formulate …

Towards Machine Self-Awareness - A Bayesian Framework For Uncertainty Propagation In Deep Neural Networks, Dimah Dera

Theses and Dissertations

Deep neural networks (DNNs) have surpassed human-level accuracy in various fields, including object recognition and classification. However, DNNs being inherently deterministic, are unable to evaluate their confidence in the decisions. Bayesian inference provides a principled approach to reason about model confidence or uncertainty by estimating the posterior distribution of the unknown parameters. The challenge in DNNs is the multi-layer stages of non-linearities, which makes propagation of high-dimensional distributions mathematically intractable. This dissertation establishes the theoretical and algorithmic foundations of uncertainty or belief propagation by developing new deep learning models that can quantify their uncertainty in the decision and self-assess their …

Efficient Hardware Implementations Of Bio-Inspired Networks, Anakha Vasanthakumaribabu

Dissertations

The human brain, with its massive computational capability and power efficiency in small form factor, continues to inspire the ultimate goal of building machines that can perform tasks without being explicitly programmed. In an effort to mimic the natural information processing paradigms observed in the brain, several neural network generations have been proposed over the years. Among the neural networks inspired by biology, second-generation Artificial or Deep Neural Networks (ANNs/DNNs) use memoryless neuron models and have shown unprecedented success surpassing humans in a wide variety of tasks. Unlike ANNs, third-generation Spiking Neural Networks (SNNs) closely mimic biological neurons by operating …

A Framework For Vector-Weighted Deep Neural Networks, Carter Chiu

UNLV Theses, Dissertations, Professional Papers, and Capstones

The vast majority of advances in deep neural network research operate on the basis of a real-valued weight space. Recent work in alternative spaces have challenged and complemented this idea; for instance, the use of complex- or binary-valued weights have yielded promising and fascinating results. We propose a framework for a novel weight space consisting of vector values which we christen VectorNet. We first develop the theoretical foundations of our proposed approach, including formalizing the requisite theory for forward and backpropagating values in a vector-weighted layer. We also introduce the concept of expansion and aggregation functions for conversion between real …

Automated Recognition Of Facial Affect Using Deep Neural Networks, Behzad Hasani

Electronic Theses and Dissertations

Automated Facial Expression Recognition (FER) has been a topic of study in the field of computer vision and machine learning for decades. In spite of efforts made to improve the accuracy of FER systems, existing methods still are not generalizable and accurate enough for use in real-world applications. Many of the traditional methods use hand-crafted (a.k.a. engineered) features for representation of facial images. However, these methods often require rigorous hyper-parameter tuning to achieve favorable results.

Recently, Deep Neural Networks (DNNs) have shown to outperform traditional methods in visual object recognition. DNNs require huge data as well as powerful computing units …