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 134 for “"DNNs"”.
-
Fully-distributed transfer learning with large DNNs on micro-controllers
Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2025-05-01
-
Exploiting and coping with sparsity to accelerate DNNs on CPUs
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2022-04-06 without embargo terms
-
End-to-end efficient deployment of DNNs: Architectural, Model, and Algorithmic Optimizations
L'abstract è presente nell'allegato / the abstract is in the attachment
-
Accelerating Quantized DNNs with Dedicated Hardware Accelerators and RISC-V Processors Using Precision-Scalable Multipliers
L'abstract è presente nell'allegato / the abstract is in the attachment
-
Mathematical Optimization Algorithms for Model Compression and Adversarial Learning in Deep Neural Networks
<p>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 …
-
Deep neural networks for choice analysis
As deep neural networks (DNNs) outperform classical discrete choice models (DCMs) in many empirical studies, one pressing question is how to reconcile them in the context of choice analysis. So far researchers mainly compare their prediction accuracy, treating them as completely different modeling …
-
Efficient and Scalable Deep Learning
<p>Deep Neural Networks (DNNs) can achieve accuracy superior to traditional machine learning models, because of their large learning capacity and the availability of large amounts of labeled data. In general, larger DNNs can obtain higher accuracy. However, there are two obstacles which hinder us …
-
Neural Network Training and Inversion with a Bregman Learning Framework
Deep Neural Networks (DNNs) are powerful computing systems that have revolutionised a wide range of research domains and have achieved remarkable success in various realworld applications over the past decade. Despite their significant recent advancements, training DNNs still remains a challenging …
-
Trustworthy and Efficient Knowledge Sharing across Tasks in Deep Neural Networks
Deep neural networks (DNNs) have revolutionized various fields with their superior performance on particular tasks. However, these tasks in real-world applications are often interrelated, raising the necessity for DNNs to share and transfer knowledge reliably and effectively between tasks. To solve …
-
Acoustic models for speech recognition using Deep Neural Networks based on approximate math
Deep Neural Networks (DNNs) are eective models for machine learning. Unfortunately, training a DNN is extremely time-consuming, even with the aid of a graphics processing unit (GPU). DNN training is especially slow for tasks with large datasets. Existing approaches for speeding up the process …
-
Adapting deep neural networks as models of human visual perception
Deep neural networks (DNNs) have recently been used to solve complex perceptual and decision tasks. In particular, convolutional neural networks (CNN) have been extremely successful for visual perception. In addition to performing well on the trained object recognition task, these CNNs also model …
-
Accelerating distributed neural network training with network-centric approach
… technique to reduce the training time of large DNNs for a wide range of applications. In existing distributed training approaches, however, the communication time to periodically exchange parameters (i.e., weights) and gradients among computer nodes over the network constitutes a large fraction …
-
Generalization of deep neural networks to unseen attribute combinations
… is it the case that deep neural networks (DNNs) are able to generalize to such novel combinations in object recognition or other related vision tasks? This thesis demonstrates that (1) the ability of DNNs to generalize to unseen attribute combinations increases with the increased diversity …
-
Evolutionary Optimization of Neural Architectures for Remaining Useful Life Prediction
… in particular employing deep neural networks (DNNs), have shown success in the RUL prediction task. However, although their architecture considerably affects performance, DNNs are usually handcrafted by human experts via a labor-intensive design process. To overcome this issue, we propose …
-
Architecture design for highly flexible and energy-efficient deep neural network accelerators
Deep neural networks (DNNs) are the backbone of modern artificial intelligence (AI). However, due to their high computational complexity and diverse shapes and sizes, dedicated accelerators that can achieve high performance and energy efficiency across a wide range of DNNs are critical for enabling …
-
Synthetic Data Generation and Sampling for Online Training of DNN in Manufacturing Supervised Learning Problems
… statistical models such as Deep Neural Networks (DNNs). Deep Neural Networks (DNNs) have proven to be remarkably effective in supervised learning in critical manufacturing applications, such as AI-enabled automatic inspection, quality modeling, etc. However, there is a lack of performance …
-
The Effect Of Hyperparameters In The Activation Layers Of Deep Neural Networks
Deep neural networks (DNNs), and artificial neural networks (ANNs) in general, have recently received a great amount of attention from both the media and the machine learning community at large. DNNs have been used to produce world-class results in a variety of domains, including image recognition, …
-
Towards Understanding Human-aligned Neural Representation in the Presence of Confounding Variables
Deep Neural Networks (DNNs) find one out of many possible solutions to a given task such as classification. This solution is more likely to pick up on spurious features and low-level statistical patterns in the train data rather than semantic features and highlevel abstractions, resulting in poor …
-
Provably reliable machine learning systems
… which primarily use deep neural networks (DNNs), serve as critical components in safety-critical applications and compound AI systems. Despite their ubiquity, automated formal reasoning about their reliability has lagged significantly. Neural network verification is NP-hard, requiring …
-
Investigating the Role of Biological Constraints in Adversarial Robustness via Modeling and Representational Geometry
Although deep neural networks (DNNs) achieve excellent performance and even outperform humans on various computer vision tasks, the robustness of DNNs to small perturbations is still far from being comparable to the human visual system. Indeed, adversarial attacks, which are very small worst-case …
Page 1 of 7