Boolean Variation and Boolean Logic BackPropagation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Nguyen, Van Minh
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911869159079936
author Nguyen, Van Minh
author_facet Nguyen, Van Minh
contents The notion of variation is introduced for the Boolean set and based on which Boolean logic backpropagation principle is developed. Using this concept, deep models can be built with weights and activations being Boolean numbers and operated with Boolean logic instead of real arithmetic. In particular, Boolean deep models can be trained directly in the Boolean domain without latent weights. No gradient but logic is synthesized and backpropagated through layers.
format Preprint
id arxiv_https___arxiv_org_abs_2311_07427
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Boolean Variation and Boolean Logic BackPropagation
Nguyen, Van Minh
Machine Learning
Discrete Mathematics
Logic in Computer Science
Optimization and Control
The notion of variation is introduced for the Boolean set and based on which Boolean logic backpropagation principle is developed. Using this concept, deep models can be built with weights and activations being Boolean numbers and operated with Boolean logic instead of real arithmetic. In particular, Boolean deep models can be trained directly in the Boolean domain without latent weights. No gradient but logic is synthesized and backpropagated through layers.
title Boolean Variation and Boolean Logic BackPropagation
topic Machine Learning
Discrete Mathematics
Logic in Computer Science
Optimization and Control
url https://arxiv.org/abs/2311.07427