Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 27 for “"Deep Learning Optimization"”.
-
Deep Learning Optimization and Acceleration
The novelty of this dissertation is the optimization and acceleration of deep neural networks aimed at real-time predictions with minimal energy consumption. It consists of cross-layer optimization, output directed dynamic quantization, and opportunistic near-data computation for deep neural …
-
Optimization and Loss Landscape Geometry of Deep Learning
The impressive success of deep learning is powered by models that are rapidly growing in size along with the computational resources that are used to train them. Despite these growing demands, the dominant tools used to train these networks have not evolved significantly to match these needs. One …
-
Design Optimization of Switched Reluctance Motors Using Deep Learning
… To address this problem, this thesis applies a Deep Learning optimization approach to minimize the torque ripple and maximize the average torque by changing the stator and rotor pole arc angles, 𝛽𝑠 and 𝛽𝑟 respectively, using Convolutional Neural Networks (CNNs) and Generative Adversarial …
-
Robust Deep Learning on Graphs
… deluge'' has sparked the interest in graph-based learning methods and their application in a number of disciplines ranging from sociology and biology to transportation or communications. Realizing the potential of graph-based learning has never been closer, even though formidable challenges are …
-
Learning under Test-Time Feedback: Reduction, Learning, Optimization
… deploying models sequentially, such as in robot learning and language modeling. So far, the dominant, scalable recipe involves amassing demonstration data, such as human teleoperation or internet text, and training a neural network via a one-step prediction objective along the demonstration …
-
Geometry, Reflectance and Lighting from Neural Rendering
… presents six novel contributions that leverage deep learning, optimization, and neural rendering techniques, and solve such challenging real-world problems in computer vision and graphics. Our methods can handle diverse factors involved in image formation processes, including unknown lighting, …
-
REAL-TIME TWEET SENTIMENT ANALYSIS BASED ON DEEP LEARNING
… etc, aiming to improve the products or services. Deep learning models have shown state-of-the-art accuracy for sentiment. However, they incur high computational cost, which is a big challenge for real-time deployment over large-scale data streams. Towards this challenge, in this thesis, I propose …
-
Material Management Framework utilizing Near Real-Time Monitoring of Construction Operations
… which is the data analysis and reporting model, Deep Learning (DL) and image processing algorithms are proposed to visualize and detect actual progress in terms of built elements in near real-time. In contrast with the other studies in which conventional computer vision algorithms are often used …
-
SECURE PERSONAL HEALTHCARE USING FINE-GRAINED PPG-BASED SENSING AND DEEP LEARNING
… healthcare data on mobile devices. Moreover, deep learning (DL) technologies bring unique opportunities and challenges to create more robust and smarter models directly on resource-constrained mobile devices that are tailored specifically for personal healthcare applications.Recently, advanced …
-
Understanding Deep Learning via Tractable Models
Deep learning systems have transformed information processing, achieving remarkable success in domains ranging from computer vision to natural language processing, and are completely reshaping every sector of the industry. Yet, our theoretical understanding of why these systems work lags far behind …
-
HEPPO: Hardware-Efficient Proximal Policy Optimization. A Universal Pipelined Architecture for Generalized Advantage Estimation
… HEPPO: Hardware-Efficient Proximal Policy Optimization, a framework designed to address the computational and memory challenges associated with implementing advanced reinforcement learning algorithms on resource-constrained hardware platforms. By introducing dynamic standardization for …
-
Využití strojového učení při simulaci mechanického chování materiálů
Diplomová práce se zabývá možností využití modelů strojového učení pro určování efektivních makroskopických materiálových charekteristik vícefázových materiálů. Po představení metody homogenizace asymptotickým rozvojem je s jejím využitím vytvořen na základě metody konečných prvků software v jazyce …
-
Side information, robustness, and self supervision in imitation learning
Imitation learning refers to a family of learning algorithms enabling the learning agents to learn directly from demonstrations provided by experts, practitioners, and users. While imitation learning methods have been successfully applied to many robot learning and autonomous driving problems, …
-
Reducing Manual Intervention in Deep Learning
Deep learning practitioners face numerous manual decisions throughout the model development pipeline, from selecting hyperparameters and optimization algorithms to evaluating model capabilities. These decisions often require extensive expertise and computational resources, creating barriers to …
-
Model-based Deep Learning for Computational Imaging
This dissertation addresses model-based deep learning for computational imaging. The motivation of our work is driven by the increasing interests in the combination of imaging model, which provides data-consistency guarantees to the observed measurements, and deep learning, which provides advanced …
-
Model-based Deep Learning for Computational Imaging
This dissertation addresses model-based deep learning for computational imaging. The motivation of our work is driven by the increasing interests in the combination of imaging model, which provides data-consistency guarantees to the observed measurements, and deep learning, which provides advanced …
-
Using Neural Networks to Maximize a Submodular Function
It is accurate to say that optimization plays a huge role in the field of machine learning. Majority of the machine learning problems can be reduced to optimization problems and having the ability to solve such group of optimization problems be- comes the goal of all the people who are interested …
-
Real-Time Feedback-Driven Framework For Automated Cybersickness Mitigation
… (FMS), and others. Recently, machine learning approaches have also been adopted to predict CS but to the best of our knowledge, there is no research work to mitigate the user's CS based on the physiological data during immersive moments. To bridge this gap, in this study, we propose a …
Page 1 of 2