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"”.

  1. 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

    uiuc Repository record for Fully-distributed transfer learning with large DNNs on micro-controllers (opens in a new tab)

  2. 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

    uiuc Repository record for Exploiting and coping with sparsity to accelerate DNNs on CPUs (opens in a new tab)

  3. 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 …

    syracuse-diss Repository record for Mathematical Optimization Algorithms for Model Compression and Adversarial Learning in Deep Neural Networks (opens in a new tab)

  4. 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 …

    mit Repository record for Deep neural networks for choice analysis (opens in a new tab)

  5. 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 …

    duke Repository record for Efficient and Scalable Deep Learning (opens in a new tab)

  6. 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 …

    cambridge Repository record for Neural Network Training and Inversion with a Bregman Learning Framework (opens in a new tab)

  7. 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 …

    uts Repository record for Trustworthy and Efficient Knowledge Sharing across Tasks in Deep Neural Networks (opens in a new tab)

  8. 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 …

    mit Repository record for Acoustic models for speech recognition using Deep Neural Networks based on approximate math (opens in a new tab)

  9. 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 …

    cambridge Repository record for Adapting deep neural networks as models of human visual perception (opens in a new tab)

  10. 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 …

    uiuc Repository record for Accelerating distributed neural network training with network-centric approach (opens in a new tab)

  11. 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 …

    mit Repository record for Generalization of deep neural networks to unseen attribute combinations (opens in a new tab)

  12. 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 …

    trento Repository record for Evolutionary Optimization of Neural Architectures for Remaining Useful Life Prediction (opens in a new tab)

  13. 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 …

    mit Repository record for Architecture design for highly flexible and energy-efficient deep neural network accelerators (opens in a new tab)

  14. 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 …

    vt Repository record for Synthetic Data Generation and Sampling for Online Training of DNN in Manufacturing Supervised Learning Problems (opens in a new tab)

  15. 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, …

    mississippi Repository record for The Effect Of Hyperparameters In The Activation Layers Of Deep Neural Networks (opens in a new tab)

  16. 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 …

    mit Repository record for Towards Understanding Human-aligned Neural Representation in the Presence of Confounding Variables (opens in a new tab)

  17. 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 …

    uiuc Repository record for Provably reliable machine learning systems (opens in a new tab)

  18. 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 …

    mit Repository record for Investigating the Role of Biological Constraints in Adversarial Robustness via Modeling and Representational Geometry (opens in a new tab)

Page 1 of 7