Compression strategies and space-conscious representations for deep neural networks

07/15/2020
by   Giosuè Cataldo Marinò, et al.
0

Recent advances in deep learning have made available large, powerful convolutional neural networks (CNN) with state-of-the-art performance in several real-world applications. Unfortunately, these large-sized models have millions of parameters, thus they are not deployable on resource-limited platforms (e.g. where RAM is limited). Compression of CNNs thereby becomes a critical problem to achieve memory-efficient and possibly computationally faster model representations. In this paper, we investigate the impact of lossy compression of CNNs by weight pruning and quantization, and lossless weight matrix representations based on source coding. We tested several combinations of these techniques on four benchmark datasets for classification and regression problems, achieving compression rates up to 165 times, while preserving or improving the model performance.

READ FULL TEXT
research
08/28/2021

Compact representations of convolutional neural networks via weight pruning and quantization

The state-of-the-art performance for several real-world problems is curr...
research
01/18/2021

Deep Compression of Neural Networks for Fault Detection on Tennessee Eastman Chemical Processes

Artificial neural network has achieved the state-of-art performance in f...
research
02/17/2023

Less is More: The Influence of Pruning on the Explainability of CNNs

Modern, state-of-the-art Convolutional Neural Networks (CNNs) in compute...
research
06/11/2021

DECORE: Deep Compression with Reinforcement Learning

Deep learning has become an increasingly popular and powerful option for...
research
09/29/2015

Compression of Deep Neural Networks on the Fly

Thanks to their state-of-the-art performance, deep neural networks are i...
research
07/09/2021

Joint Matrix Decomposition for Deep Convolutional Neural Networks Compression

Deep convolutional neural networks (CNNs) with a large number of paramet...
research
01/27/2022

An Empirical Analysis of Recurrent Learning Algorithms In Neural Lossy Image Compression Systems

Recent advances in deep learning have resulted in image compression algo...

Please sign up or login with your details

Forgot password? Click here to reset