Uncertainty-based quantization method for stable training of binary neural networks
Binary neural networks (BNNs) have gained attention due to their computational efficiency. However, training BNNs has proven to be challenging. Existing algorithms either fail to produce stable and high-quality results or are overly complex for practical use. In this paper, we introduce a novel quan...
Saved in:
Main Authors: | A.V. Trusov, D.N. Putintsev, E.E. Limonova |
---|---|
Format: | Article |
Language: | English |
Published: |
Samara National Research University
2024-08-01
|
Series: | Компьютерная оптика |
Subjects: | |
Online Access: | https://www.computeroptics.ru/eng/KO/Annot/KO48-4/480412e.html |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
The Eclipsing Binaries via Artificial Intelligence. II. Need for Speed in PHOEBE Forward Models
by: Marcin Wrona, et al.
Published: (2025-01-01) -
Closed-form interpretation of neural network classifiers with symbolic gradients
by: Sebastian J Wetzel
Published: (2025-01-01) -
MODELING OF SOLAR RADIATION WITH A NEURAL NETWORK
by: VALENTIN STOYANOV, et al.
Published: (2018-09-01) -
Protocol-based set-membership state estimation for linear repetitive processes with uniform quantization: a zonotope-based approach
by: Minghao Gao, et al.
Published: (2025-01-01) -
Slax: a composable JAX library for rapid and flexible prototyping of spiking neural networks
by: Thomas M Summe, et al.
Published: (2025-01-01)