Learning Sparse Low-Precision Neural Networks With Learnable Regularization
We consider learning deep neural networks (DNNs) that consist of low-precision weights and activations for efficient inference of fixed-point operations. In training low-precision networks, gradient descent in the backward pass is performed with high-precision weights while quantized low-precision w...
Main Authors: | Yoojin Choi, Mostafa El-Khamy, Jungwon Lee |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9098870/ |
Similar Items
-
Exploring Accumulated Gradient-Based Quantization and Compression for Deep Neural Networks
by: Gaopande, Meghana Laxmidhar
Published: (2020) -
Learning Sparse Convolutional Neural Network via Quantization With Low Rank Regularization
by: Xin Long, et al.
Published: (2019-01-01) -
Optimized Compression for Implementing Convolutional Neural Networks on FPGA
by: Min Zhang, et al.
Published: (2019-03-01) -
Ps and Qs: Quantization-Aware Pruning for Efficient Low Latency Neural Network Inference
by: Benjamin Hawks, et al.
Published: (2021-07-01) -
Deep Learning Models Compression for Agricultural Plants
by: Arnauld Nzegha Fountsop, et al.
Published: (2020-09-01)