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 29 for “"model compression"”.

  1. Model Compression and AutoML for Efficient Click-Through Rate Prediction

    … response for recommender systems. However, these model architectures are often effective at the cost of large computational, and memory, cost. This limits their ability to run on edge devices with smaller hardwares, such as smartphones, which is a popular use case for recommender systems. We …

    mit Repository record for Model Compression and AutoML for Efficient Click-Through Rate Prediction (opens in a new tab)

  2. Mathematical Optimization Algorithms for Model Compression and Adversarial Learning in Deep Neural Networks

    … 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 …

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

  3. Information-theoretic bounds in learning algorithms

    … in practice, we then study the problem of model change detection. There are two sets of samples that are generated according to a pre-change probabilistic model with parameter theta, and a post-change model with parameter theta', respectively. The goal is to detect whether the change in the …

    uiuc Repository record for Information-theoretic bounds in learning algorithms (opens in a new tab)

  4. Learning with generalized negative dependence : probabilistic models of diversity for machine learning

    … learning problems that require a theoretical model of diversification. Examples of such problems include experimental design and model compression: subset-selection problems that require carefully balancing the quality of each selected element with the diversity of the subset as a whole. …

    mit Repository record for Learning with generalized negative dependence : probabilistic models of diversity for machine learning (opens in a new tab)

  5. 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)

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

    … proposed from dedicated hardware platforms to model compression algorithms. Recently, hardware-aware quantization algorithms have shown further improvement in the energy efficiency of DNN by considering hardware architectures and algorithms together. In this work, a genetic algorithm-based …

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

  7. FairML : ToolBox for diagnosing bias in predictive modeling

    Predictive models are increasingly deployed for the purpose of determining access to services such as credit, insurance, and employment. Despite societal gains in efficiency and productivity through deployment of these models, potential systemic flaws have not been fully addressed, particularly the …

    mit Repository record for FairML : ToolBox for diagnosing bias in predictive modeling (opens in a new tab)

  8. MODEL ADAPTATION FOR EDGE AI

    … due to their computational demands. Existing model compression techniques often fall short by being oblivious to downstream user-specific tasks. This thesis addresses the challenge of adapting DNN models effectively on resource-limited hardware, advocating for flexible and efficient models. …

    nus Repository record for MODEL ADAPTATION FOR EDGE AI (opens in a new tab)

  9. Hardware software co-design of machine learning accelerators using univariate functions

    … techniques for hardware-awaretraining and model compression using univariate functions. First, we optimize hardware using a simple constant coefficient multiplier on Hybrid Binary-Unary (HBUNN) architecture, which offers variable hardware costs for constant coefficients. By applying …

    umn Repository record for Hardware software co-design of machine learning accelerators using univariate functions (opens in a new tab)

  10. Information theory meets big data: Theory, algorithms and applications to deep learning

    … tools to improve training algorithms and model compression algorithms in deep learning.

    uiuc Repository record for Information theory meets big data: Theory, algorithms and applications to deep learning (opens in a new tab)

  11. Privacy-aware Federated Learning with Global Differential Privacy

    … communication reduction techniques, namely, model compression, partial device participation, and periodic aggregation. Furthermore, the convergence of federated learning systems is also affected by data heterogeneity. Federated learning systems are capable of protecting the private data of …

    vt Repository record for Privacy-aware Federated Learning with Global Differential Privacy (opens in a new tab)

  12. Neuromorphic Systems for Pattern Recognition and Uav Trajectory Planning

    … performance of a recurrent belief propagation model. We first develop a probabilistic inference network to post process the recognition results of deep Convolutional Neural Network (CNN) (e.g. LeNet) and collect individual characters to form words. The output of the inference network is a set …

    syracuse-diss Repository record for Neuromorphic Systems for Pattern Recognition and Uav Trajectory Planning (opens in a new tab)

  13. Neuromorphic Systems For Pattern Recognition And Uav Trajectory Planning

    … performance of a recurrent belief propagation model. We first develop a probabilistic inference network to post process the recognition results of deep Convolutional Neural Network (CNN) (e.g. LeNet) and collect individual characters to form words. The output of the inference network is a set …

    syracuse-diss Repository record for Neuromorphic Systems For Pattern Recognition And Uav Trajectory Planning (opens in a new tab)

  14. Scaling Laws for Deep Learning

    … governed by scaling laws — for state of the art models and tasks, spanning image classification and language modeling, as well as for state of the art model compression via iterative pruning. Predictability, via the establishment of these scaling laws, provides the path for principled design and …

    mit Repository record for Scaling Laws for Deep Learning (opens in a new tab)

  15. Taming TinyML: deep learning inference at computational extremes

    The advanced data modelling capabilities of neural networks allowed deep learning to become a cornerstone of many applications of artificial intelligence (AI). AI can be brought into our environments by deploying neural models to ubiquitous Internet-of-Things (IoT), wearable and embedded devices to …

    cambridge Repository record for Taming TinyML: deep learning inference at computational extremes (opens in a new tab)

  16. TwinDNN: A tale of two deep neural networks

    Compression 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)

  17. Exploring Accumulated Gradient-Based Quantization and Compression for Deep Neural Networks

    … also achieving significant pruning, leading to model compression. We use the total accumulated absolute gradient over the training process as the indicator of importance of a parameter to the network. The most important parameters are quantized by the smallest amount. The post-training …

    vt Repository record for Exploring Accumulated Gradient-Based Quantization and Compression for Deep Neural Networks (opens in a new tab)

  18. Advances in Compression using Probabilistic Models

    … and storage necessitate the use of efficient compression methods. Compression algorithms work by mapping data to a more compact representation from which the original data can be recovered. To operate efficiently, they need to capture the characteristics of the data distribution, which can be …

    cambridge Repository record for Advances in Compression using Probabilistic Models (opens in a new tab)

  19. Co-Designing Efficient Systems and Algorithms for Sparse and Quantized Deep Learning Computing

    Deep learning models are becoming increasingly complex, expanding from 1D text and 2D images to 3D point clouds, while their size continues to grow exponentially. This trend highlights the need for greater efficiency. This thesis systematically explores efficiency in two resource-intensive …

    mit Repository record for Co-Designing Efficient Systems and Algorithms for Sparse and Quantized Deep Learning Computing (opens in a new tab)

Page 1 of 2