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 42 for “"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 of …
-
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 …
-
Network compression via network memory: fundamental performance limits
… the fundamental performance limits of universal compression of this massive data at the packet level using universal compression just above layer 3 of the network when the intermediate network nodes are enabled with the capability of memorizing the previous traffic. Universality of compression …
-
Network compression via network memory: realization principles and coding algorithms
… of redundancy elimination methods in data networks. Redundancy elimination provides a powerful technique to improve the efficiency of network links in the face of redundant data. In this work, the concept of network compression is introduced to address the redundancy elimination problem. …
-
Reducing Training Cost and Improving Inference Speed Through Neural Network Compression
… 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
… 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 issues …
-
Optimizing bandwidth of tactical communications systems
Current tactical networks are oversaturated, often slowing systems down to unusable speeds. Utilizing data collected from major exercises and Operation Iraqi Freedom II (OIF II), a typical model of existing tactical network performance is modeled and analyzed using NETWARS, a DISA sponsored …
-
Deep Grassmann Manifold Optimization for Computer Vision
… 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 experiments. …
-
Efficient Deep Learning and Its Applications
<p>Deep neural networks (DNNs) have achieved huge successes in various tasks such as object classification and detection, image synthesis, game-playing, and biological developmental system simulation. State-or-the-art performance on these tasks is usually achieved by designing deeper and wider DNNs …
-
Deep learning models for mobile and wearable biometrics
… conduct a thorough analysis of existing neural network compression techniques applied standalone and in combination for ocular-based user authentication and facial recognition.
-
Symmetrical Multilevel Diversity Coding with an All-Access Encoder
… Multilevel Diversity Coding (SMDC) is a network compression problem for which a simple separate coding strategy known as superposition coding is optimal in terms of achieving the entire admissible rate region. Carefully constructed induction argument along with the classical subset …
-
Fault detection and classification of industrial processes using lSTM neural networks with data compression techniques
… 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 usage and …
-
Design and optimization of multi-operand ring resonator based efficient optical recurrent neural network
… circuits further boosts these optical neural networks (ONNs) and endows the deployment of optical computing in real-world applications with more realistic values. Among different kinds of neural networks, recurrent neural networks (RNNs) are specially designed for processing sequence …
-
Dynamic Analysis of Recurrent Neural Networks
… 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 the …
-
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. …
-
Comparing Learned Representations Between Unpruned and Pruned Deep Convolutional Neural Networks
While deep neural networks have shown impressive performance in computer vision tasks, natural language processing, and other domains, the sizes and inference times of these models can often prevent them from being used on resource-constrained systems. Furthermore, as these networks grow larger in …
-
Visual representation learning for document image recognition
… 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 create …
-
Advanced Structures and Compositions for 3D Forming of Cellulosic Fibers
… of high- and low-solids content, (b) in-plane compression of paper webs followed by unrestrained drying and (c) chemical modification of fiber joints by protein spraying. The mechanical treatment of fiber suspensions at elevated temperature and high solids content induced permanent fiber …
Page 1 of 3