Hardware-Based Real-Time Deep Neural Network Lossless Weights Compression
Deep Neural Networks (DNN) are widely applied to many mobile applications demanding real-time implementation and large memory space. Therefore, it presents a new challenge for low-power and efficient implementation of a diversity of applications, such as speech recognition and image classification,...
Main Authors: | Tomer Malach, Shlomo Greenberg, Moshe Haiut |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9253521/ |
Similar Items
-
Stream-Based Lossless Data Compression Applying Adaptive Entropy Coding for Hardware-Based Implementation
by: Shinichi Yamagiwa, et al.
Published: (2020-06-01) -
PCBMS: A Model to Select an Optimal Lossless Image Compression Technique
by: Md. Atiqur Rahman, et al.
Published: (2021-01-01) -
Adaptive Pipeline Hardware Architecture Design and Implementation for Image Lossless Compression/Decompression Based on JPEG-LS
by: Fangjia Liu, et al.
Published: (2024-01-01) -
Linearization Weight Compression and In-Situ Hardware-Based Decompression for Attention-Based Neural Machine Translation
by: Mijin Go, et al.
Published: (2023-01-01) -
Low-cost ANS encoder for lossless data compression in FPGAs
by: Magdalena Pastuła, et al.
Published: (2024-03-01)