Title | ||
---|---|---|
SIMPLE DEEP LEARNING NETWORK VIA TENSOR-TRAIN HAAR-WAVELET DECOMPOSITION WITHOUT RETRAINING |
Abstract | ||
---|---|---|
Deep neural network has revolutionized machine learning recently. However, it suffers from both high computation and memory cost such that deploying it on a hardware with limited resources (e.g., mobile devices) becomes a challenge. To address this problem, we propose a new technique, called Tensor-Train Haar-wavelet decomposition, that decomposes a large weight tensor from a fully-connected layer into a sequence of partial Haar-wavelet matrices without retraining. The novelty originates from the deterministic partial Haar-wavelet matrices such that we only need to store row indices instead of the whole matrix. Empirical results demonstrate that our method achieves efficient model compression while maintaining limited accuracy loss, even without retraining. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/MLSP.2018.8516987 | 2018 IEEE 28th International Workshop on Machine Learning for Signal Processing (MLSP) |
Keywords | Field | DocType |
high computation,memory cost,mobile devices,weight tensor,deterministic partial Haar-wavelet matrices,simple deep learning network,neural network,machine learning,tensor-train Haar-wavelet decomposition | Tensor,Pattern recognition,Matrix (mathematics),Computer science,Algorithm,Mobile device,Artificial intelligence,Haar wavelet,Novelty,Deep learning,Artificial neural network,Computation | Conference |
ISSN | ISBN | Citations |
1551-2541 | 978-1-5386-5478-1 | 0 |
PageRank | References | Authors |
0.34 | 0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Wei-Zhi Huang | 1 | 0 | 0.34 |
Sung-Hsien Hsieh | 2 | 48 | 13.71 |
Chun-shien Lu | 3 | 1238 | 104.71 |
Soo-Chang Pei | 4 | 2054 | 241.11 |