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 25 for “"Neural network compression"”.
-
Convolutional neural network compression via tensor decomposition
… systems. Since the advent of the AlexNet neural network model in 2012, convolutional neural networks have been demonstrated to be very effective at performing many computer vision tasks. However, convolutional neural networks’ high computational and storage costs hinder the wider adoption …
-
Deep Neural Network Compression with Filter Pruning
The rapid development of convolutional neural networks (CNNs) in computer vision tasks has inspired researchers to apply their potential to embedded or mobile devices. However, it typically requires a large amount of computation and memory footprint, limiting their deployment in those …
-
Reducing Training Cost and Improving Inference Speed Through Neural Network Compression
… solve these problems, a new research area of neural network compression has emerged. Techniques like quantization, pruning, and model distillation have become standard. However, these methods have several drawbacks. Many of these techniques require specialized hardware for inference, reduce …
-
Numerical Linear Algebra for Scientific Machine Learning: Neural Network Compression and Continuous Trace Estimation
… (2). INTRIM (IN-Training Iterative Model) Compression interleaves neural network training with repeated compression steps to remove excess capacity, reducing both training and inference time while maintaining accuracy. PruningAMR is an algorithm for efficiently visualizing implicit neural …
-
Towards fair and efficient distributed intelligence
… to enhance our world through the use of Deep Neural Networks (DNNs). However, modern DNNs suffer from high computational complexity and are often relegated to specialized hardware, a bottleneck which has severely limited their practical use. In this work, we contribute to improving these …
-
Deep learning models for mobile and wearable biometrics
… we conduct a thorough analysis of existing neural network compression techniques applied standalone and in combination for ocular-based user authentication and facial recognition.
-
Fault detection and classification of industrial processes using lSTM neural networks with data compression techniques
… Then, we train a Long Short-Term Memory (LSTM) neural network with those compressed inputs to perform fault detection. Finally, the second approach addresses efficient edge computing systems, performing LSTM neural network compression with pruning technique. The compression reduces the memory …
-
Dynamic Analysis of Recurrent Neural Networks
With the advancement in deep learning research, neural networks have become one of the most powerful tools for artificial intelligence tasks. More specifically, recurrent neural networks (RNNs) have achieved state-of-the-art in tasks such as hand-writing recognition and speech recognition. Despite …
-
Visual representation learning for document image recognition
… of this thesis is the study of Convolutional Neural Networks (CNNs) for the word detection problem along with their generalization capability, i.e.if it is possible to generate transferable and discriminative deep features. To this end, we propose several modified architectures in order to …
-
Deep Grassmann Manifold Optimization for Computer Vision
… embeddings, visual domain adaptation, and deep neural network compression. We combine concepts from the fields of manifold geometry and deep learning to develop cutting edge methods in each of these areas. Each of the methods proposed in this work achieves state-of-the-art results in our …
-
Designing for Deployable, Secure, and Generic Machine Learning Systems
… and security vulnerabilities inherent in deep neural networks. Moreover, the deployment of deep neural network models remains a significant hurdle. This dissertation introduces a multimedia prototyping framework tailored for visual analytical applications, improving the reusability of video …
-
Fast and compact neural network via Tensor-Train reparameterization
… of challenges for deep learning training. Large neural network layers can be parameterized based on tensor decomposition to compress model size, but at the potential costs of degraded accuracy and more execution time to reconstruct the layer parameters from the tensorized representation. In this …
-
Efficient Convolutional Neural Networks for Image Classification and Regression
Neural networks have been a topic of research since 1970s and the Convolutional Neural Networks (CNNs) were first shown to work well for hand written digits recognition in 1998. These early networks were however still shallow and contained only a few layers. Moreover these networks were mostly …
-
Towards Efficient Deep Learning: From Compression, Search to Unification
… multimodal understanding, etc. Meanwhile, deep neural networks are usually parameter-heavy, inefficient, and highly specialized. As a result, there has been a growing demand to improve the efficiency and interoperability of deep neural networks motivated by different needs. In this dissertation, …
-
Towards Artificially Intelligent Communications
… (interpretability & generalizability), (2) neural network pruning methods enabling edge-ready AI (interpretability & deployability), and (3) a gray-box, physics-based AI simulation tool for fiber optic networks (interpretability & generalizability). This thesis demonstrates advancements in …
-
An Information-Theoretic Approach to Optimal Neural-Network-Based Compression
Modern artificial-neural-network-based (ANN-based) compressors have recently achieved notable successes on compressing multimedia formats such as images. This is despite information-theoretic near-optimality results of the linear transform coding paradigm, which forms the basis of existing standard …
-
Structural pruning of convolutional neural networks for efficient and sustainable model optimization
The proliferation of Deep Convolutional Neural Networks (CNNs) has fundamentally transformed the landscape of computer vision and autonomous systems. However, the state-of-the-art performance of these models is largely predicated on extreme over-parameterization, leading to a "Red AI" paradigm …
-
Privacy preserving and efficient machine learning algorithms
… deep learning efficiently, specifically Deep Neural Networks (DNNs), which are the core of deep learning. In this dissertation, we focus on achieving efficiency by reducing the computational cost of DNNs in multiple ways. This thesis first tackles the privacy concerns arising from deep …
-
Komprese difuzních modelů pro generování obrazu
Táto diplomová práca sa zameriava na optimalizáciu výpočtovej efektívnosti generatívnych difúznych modelov skrz vyhodnotenie konvenčných metód komprimácie neurónovych sieti na architektúre Denoising Diffusion Probabilistic Model (DDPM). Modelová komprimácia bola vykonaná na parametroch …
Page 1 of 2