Boolean Variation and Boolean Logic BackPropagation
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| 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 |