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 174 for “"DNN"”.

  1. Congestion Control for DNN training clusters

    The modern DNN workloads generate network traffic having striking differences with the conventional data-center traffic. DNN training jobs generate periodic traffic pattern where all subsequent flows depend on the completion of the currently running flow. Although this periodic behavior calls for a …

    mit Repository record for Congestion Control for DNN training clusters (opens in a new tab)

  2. An adaptive pruning algorithm for DNN compression

    In recent years, deep neural networks have achieved remarkable results in various artificial intelligence tasks such as image recognition and machine language translation. Although deep neural networks achieve state-of-the-art accuracy for various tasks, the high accuracy comes with high …

    uiuc Repository record for An adaptive pruning algorithm for DNN compression (opens in a new tab)

  3. ACCELERATING DNN INFERENCE AND TRAINING IN DISTRIBUTED SYSTEMS

    Deep Neural Network (DNN) models have been widely deployed in a variety of applications. To achieve better performance, DNN models become more and more complex, which introduces extremely long DNN training time. Although DNN inference typically runs a single round of forward propagation on the DNN

    temple Repository record for ACCELERATING DNN INFERENCE AND TRAINING IN DISTRIBUTED SYSTEMS (opens in a new tab)

  4. Energy-aware DNN Quantization for Processing-In-Memory Architecture

    … computational cost of deep neural network (DNN), many efforts to develop energy-efficient intelligent system have been proposed from dedicated hardware platforms to model compression algorithms. Recently, hardware-aware quantization algorithms have shown further improvement in the energy …

    gatech Repository record for Energy-aware DNN Quantization for Processing-In-Memory Architecture (opens in a new tab)

  5. Surface electromyography signal classification using SFDN+DNN for hand gesture recognition

    … As a result, the novel method is called SFDN+DNN. There are many complex and developed prostheses in the market. However, the bottleneck to improve the capabilities of the prostheses to a quasi-real-hand level is still a big challenge. In this thesis a thorough literature review of …

    regina Repository record for Surface electromyography signal classification using SFDN+DNN for hand gesture recognition (opens in a new tab)

  6. Reducing Global Memory Accesses in DNN Training using Structured Weight Masking

    Training large deep neural networks (DNNs) is often constrained by memory bandwidth, with frequent global memory accesses representing a significant performance bottleneck. This thesis investigates the potential of dynamic structured weight masking to alleviate this bottleneck during training, …

    heid-thes Repository record for Reducing Global Memory Accesses in DNN Training using Structured Weight Masking (opens in a new tab)

  7. Converting Autoencoder Based Energy-Efficient and Secure DNN Inference on Edge Devices

    Deep neural networks (DNNs) have become essential for computer vision tasks like image classification, object detection, and depth estimation. With the rise of embedded devices, there is a growing demand for lightweight and energy-efficient models. While DNNs outperform traditional machine learning …

    tdl Repository record for Converting Autoencoder Based Energy-Efficient and Secure DNN Inference on Edge Devices (opens in a new tab)

  8. Investigating Opportunities and Challenges in Modeling and Designing Scale-Out DNN Accelerators

    … who would like to integrate an existing DNN accelerator architecture into a larger SoC and would be interested in system-level characterization results. The second use-case is for an accelerator architect who would like to use the tool to explore the accelerator design space by sweeping …

    gatech Repository record for Investigating Opportunities and Challenges in Modeling and Designing Scale-Out DNN Accelerators (opens in a new tab)

  9. GraphPipe: Improving the Performance and Scalability of DNN Training with Graph Pipeline Parallelism

    Deep neural networks (DNNs) continue to grow rapidly in size, thus it is infeasible to train them on a single device. To address this challenge, current DNN training systems apply pipeline-parallel techniques. They split a DNN into multiple stages, construct a pipeline of them, and assign to each …

    mit Repository record for GraphPipe: Improving the Performance and Scalability of DNN Training with Graph Pipeline Parallelism (opens in a new tab)

  10. 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)

  11. Effects of Hardware Design Choices on Neural Network Accuracy in Analog Inference Accelerators

    … and high-throughput deep neural network (DNN) computations by computing in memory. Unfortunately, device and circuit nonidealities in these accelerators, such as noise and quantization, can also lead to low DNN inference accuracy due to computation errors arising from these non-idealities. …

    mit Repository record for Effects of Hardware Design Choices on Neural Network Accuracy in Analog Inference Accelerators (opens in a new tab)

  12. Software-Hardware Co-design For Deep Learning Model Acceleration

    <p>Current deep neural network (DNN) models have shown beyond-human performance in multiple artificial intelligent tasks. However, state-of-the-art DNN models still exhibit great issues on efficiency that pose significant obstacles to their practical application in real-world scenarios. To further …

    duke Repository record for Software-Hardware Co-design For Deep Learning Model Acceleration (opens in a new tab)

  13. Dynamic Neural Network-based Adaptive Inverse Optimal Control Design

    … introduces a Dynamical Neural Network (DNN) model based adaptive inverse optimal control design for a class of nonlinear systems. A DNN structure is developed and stabilized based on a control Lyapunov function (CLF). The CLF must satisfy the partial Hamilton Jacobi-Bellman (HJB) …

    siu-theses Repository record for Dynamic Neural Network-based Adaptive Inverse Optimal Control Design (opens in a new tab)

  14. Efficient, Accurate, and Flexible PIM Inference through Adaptable Low-Resolution Arithmetic

    … to efficiently run Deep Neural Network (DNN) inference by reducing costly data movement and by using resistive RAM (ReRAM) for efficient analog compute. Unfortunately, overall PIM accelerator efficiency and throughput are limited by area/energy-intensive analog-to-digital converters …

    mit Repository record for Efficient, Accurate, and Flexible PIM Inference through Adaptable Low-Resolution Arithmetic (opens in a new tab)

  15. TwinDNN: A tale of two deep neural networks

    … technologies for deep neural networks (DNNs), such as weight quantization, have been widely investigated to reduce the model size so that they can be implemented on hardware with strict resource restrictions. However, one major disadvantage of model compression is accuracy degradation. …

    uiuc Repository record for TwinDNN: A tale of two deep neural networks (opens in a new tab)

  16. Towards Secure Machine Learning Acceleration: Threats and Defenses Across Algorithms, Architecture, and Circuits

    As deep neural networks (DNNs) are widely adopted for high-stakes applications that process sensitive private data and make critical decisions, security concerns about user data and DNN models are growing. In particular, hardware-level vulnerabilities can be exploited to undermine the …

    mit Repository record for Towards Secure Machine Learning Acceleration: Threats and Defenses Across Algorithms, Architecture, and Circuits (opens in a new tab)

  17. Coordination déglutitions non nutritives-respiration lors d'un stress postnatal chez l'agneau nouveau-né : effets de l'hypoxie/hypercapnie et de la fumée secondaire

    … (SMSN). Ainsi, les déglutitions non-nutritives (DNN) se présentent comme une fonction fondamentale en période néonatale notamment pour la clairance des voies aériennes supérieures des sécrétions salivaires et des reflux laryngopharyngés. Il apparaît plus précisément que la coordination entre DNN

    sherbrooke Repository record for Coordination déglutitions non nutritives-respiration lors d'un stress postnatal chez l'agneau nouveau-né : effets de l'hypoxie/hypercapnie et de la fumée secondaire (opens in a new tab)

  18. De-noising and de-blurring of images using deep neural networks

    Deep Neural Networks (DNNs) [1] are often used for image reconstruction, but perform better reconstructing the low frequencies of the image than the high frequencies. This is especially the case when using noisy images. In this paper, we test using a Learning Synthesis Deep Neural Network (LS-DNN) …

    mit Repository record for De-noising and de-blurring of images using deep neural networks (opens in a new tab)

  19. A sensory system for robots using evolutionary artificial neural networks.

    … system, called the Distributed Neural Network (DNN) was based on the sensory-motor connections in the common toad, Bufo Bufo. The sparsely connected network architecture has features of modularity enhanced by the presence of lateral inhibitory connections. It was implemented using Evolutionary …

    rgu Repository record for A sensory system for robots using evolutionary artificial neural networks. (opens in a new tab)

  20. Investigation in modeling a load-sensing pump using dynamic neural unit based dynamic neural networks

    … neural unit (DNU) based dynamic neural network (DNN) in modeling a hydraulic component (specifically a load-sensing pump), and the model could be used in a simulation with any other required component model to aid in hydraulic system design. To be truly representative of the component, the neural …

    sask Repository record for Investigation in modeling a load-sensing pump using dynamic neural unit based dynamic neural networks (opens in a new tab)

Page 1 of 9