Back to Search
Start Over
Pruning In Time (PIT): A Lightweight Network Architecture Optimizer for Temporal Convolutional Networks
- Source :
- 2021 58th ACM/IEEE Design Automation Conference (DAC), 2021, pp. 1015-1020
- Publication Year :
- 2022
-
Abstract
- Temporal Convolutional Networks (TCNs) are promising Deep Learning models for time-series processing tasks. One key feature of TCNs is time-dilated convolution, whose optimization requires extensive experimentation. We propose an automatic dilation optimizer, which tackles the problem as a weight pruning on the time-axis, and learns dilation factors together with weights, in a single training. Our method reduces the model size and inference latency on a real SoC hardware target by up to 7.4x and 3x, respectively with no accuracy drop compared to a network without dilation. It also yields a rich set of Pareto-optimal TCNs starting from a single model, outperforming hand-designed solutions in both size and accuracy.
- Subjects :
- Computer Science - Machine Learning
Subjects
Details
- Database :
- arXiv
- Journal :
- 2021 58th ACM/IEEE Design Automation Conference (DAC), 2021, pp. 1015-1020
- Publication Type :
- Report
- Accession number :
- edsarx.2203.14768
- Document Type :
- Working Paper
- Full Text :
- https://doi.org/10.1109/DAC18074.2021.9586187