Name
Abstract | ||
|---|---|---|
This work proposes a new approach to deep neural network (DNN) compression. We employ black-box function approximation techniques from signal processing to compress. DNN, in general, can approximate non-smooth and piecewise smooth functions. With only this assumption, we model the function that the DNN has learnt as a piecewise linear function. This is a standard function approximation approach. We compared our approach with two state-of-the-art techniques - spatial singular value decomposition and channel pruning with weight reconstruction; and one of state-of-practice tool - OpenVINO. Two well known 1D DNN models for time series classification - ResNet and InceptionTime were compressed. Results show that our model yields better compression at comparable losses in accuracy on majority of the datasets. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1109/IJCNN52387.2021.9533962 | 2021 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN) |
Keywords | DocType | ISSN |
deep neural network, model compression, system identification, time series classification | Conference | 2161-4393 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Ishan Sahu | 1 | 0 | 1.01 |
| Arpan Pal | 2 | 195 | 51.41 |
| Arijit Ukil | 3 | 97 | 17.04 |
| A. Majumdar | 4 | 644 | 75.83 |