Probabilistic Automated Model Compression via Representation Mutual Information Optimization
Deep neural networks, despite their remarkable success in computer vision tasks, often face deployment challenges due to high computational demands and memory usage. Addressing this, we introduce a probabilistic framework for automated model compression (Prob-AMC) that optimizes pruning, quantizatio...
Saved in:
Main Authors: | Wenjie Nie, Shengchuan Zhang, Xiawu Zheng |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2024-12-01
|
Series: | Mathematics |
Subjects: | |
Online Access: | https://www.mdpi.com/2227-7390/13/1/108 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
HitIct:Chinese corpus for the evaluation of lossless compression algorithms
by: CHANG Wei-ling1, et al.
Published: (2009-01-01) -
THEORETICAL ANALYSIS OF INFLUENTIAL PARAMETERS TO COMPRESSION AND DECOMPRESSION PROCESS OF COMPRESSED OIL IN HYDRAULIC SYSTEMS OF THE PRESS
by: MILUTIN ŽIVKOVIĆ
Published: (2016-06-01) -
Investigation on the Compressibility Factor of Hydrogen-Doped Natural Gas Using GERG-2008 Equation of State
by: Ji-Chao Li, et al.
Published: (2024-12-01) -
Mutual information power analysis attack in the frequency domain of the crypto chip
by: Min WANG, et al.
Published: (2015-11-01) -
A discrete event simulation model of compressive creep for LDPE
by: Seyyed Saeed Vaezzadeh, et al.
Published: (2025-03-01)