Zobrazeno 1 - 10
of 6 720
pro vyhledávání: '"Network compression"'
Autor:
Mango, John, Katende, Ronald
This paper introduces a dynamic, error-bounded hierarchical matrix (H-matrix) compression method tailored for Physics-Informed Neural Networks (PINNs). The proposed approach reduces the computational complexity and memory demands of large-scale physi
Externí odkaz:
http://arxiv.org/abs/2409.07028
We present TropNNC, a framework for compressing neural networks with linear and convolutional layers and ReLU activations. TropNNC is a structured compression framework based on a geometrical approach to machine/deep learning, using tropical geometry
Externí odkaz:
http://arxiv.org/abs/2409.03945
Despite their high accuracy, complex neural networks demand significant computational resources, posing challenges for deployment on resource-constrained devices such as mobile phones and embedded systems. Compression algorithms have been developed t
Externí odkaz:
http://arxiv.org/abs/2409.03555
Deep neural networks typically impose significant computational loads and memory consumption. Moreover, the large parameters pose constraints on deploying the model on edge devices such as embedded systems. Tensor decomposition offers a clear advanta
Externí odkaz:
http://arxiv.org/abs/2408.16289
Neural network pruning is a rich field with a variety of approaches. In this work, we propose to connect the existing pruning concepts such as leave-one-out pruning and oracle pruning and develop them into a more general Shapley value-based framework
Externí odkaz:
http://arxiv.org/abs/2407.15875
Autor:
Wang, Xinren1 (AUTHOR), Hu, Dongming1 (AUTHOR), Fan, Xueqi1 (AUTHOR), Liu, Huiyi2 (AUTHOR), Yang, Chenbin2 (AUTHOR) yangchenbin@hhu.edu.cn
Publikováno v:
Symmetry (20738994). Nov2024, Vol. 16 Issue 11, p1461. 19p.
Binary Neural Networks (BNNs) enable efficient deep learning by saving on storage and computational costs. However, as the size of neural networks continues to grow, meeting computational requirements remains a challenge. In this work, we propose a n
Externí odkaz:
http://arxiv.org/abs/2407.12075
Autor:
Thrash, Chayne, Abbasi, Ali, Nooralinejad, Parsa, Koohpayegani, Soroush Abbasi, Andreas, Reed, Pirsiavash, Hamed, Kolouri, Soheil
The outstanding performance of large foundational models across diverse tasks-from computer vision to speech and natural language processing-has significantly increased their demand. However, storing and transmitting these models pose significant cha
Externí odkaz:
http://arxiv.org/abs/2406.19301
In real applications of Reinforcement Learning (RL), such as robotics, low latency and energy efficient inference is very desired. The use of sparsity and pruning for optimizing Neural Network inference, and particularly to improve energy and latency
Externí odkaz:
http://arxiv.org/abs/2405.07748
Deep Neural Networks (DNNs) have achieved remarkable success in addressing many previously unsolvable tasks. However, the storage and computational requirements associated with DNNs pose a challenge for deploying these trained models on resource-limi
Externí odkaz:
http://arxiv.org/abs/2405.03089