Can I read Compression Strategies and Space-conscious Representations for Deep Neural Networks on EtoBox?

Compression Strategies and Space-conscious Representations for Deep Neural Networks by Marinò, Giosuè Cataldo; Ghidoli, Gregorio; Frasca, Marco; Malchiodi, Dario is a scholarly article available to read on EtoBox.

What is Compression Strategies and Space-conscious Representations for Deep Neural Networks about?

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.

Author

Marinò, Giosuè Cataldo; Ghidoli, Gregorio; Frasca, Marco; Malchiodi, Dario

Published

2020

Language

EN