paper-with-me

Papers

Boolean Variation and Boolean Logic BackPropagation

2023-11-13 · Van Minh Nguyen

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.

📄 PDF Abstract BibTeX arXiv:2311.07427

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Boolean Logic as an Error feedback mechanism

2024-01-29 · Louis Leconte

The notion of Boolean logic backpropagation was introduced to build neural networks with weights and activations being Boolean numbers. Most of computations can be done with Boolean logic instead of real arithmetic, both…

$\partial\mathbb{B}$ nets: learning discrete functions by gradient descent

2023-05-12 · Ian Wright

$\partial\mathbb{B}$ nets are differentiable neural networks that learn discrete boolean-valued functions by gradient descent. $\partial\mathbb{B}$ nets have two semantically equivalent aspects: a differentiable soft-net…

Binarization

BOLD: Boolean Logic Deep Learning

2024-05-25 · Van Minh Nguyen, Cristian Ocampo, Aymen Askri, Louis Leconte 외

Deep learning is computationally intensive, with significant efforts focused on reducing arithmetic complexity, particularly regarding energy consumption dominated by data movement. While existing literature emphasizes i…

BenchmarkingDeep LearningImage Super-ResolutionNatural Language Understanding+2

Gate-level boolean evolutionary geometric attention neural networks

2025-11-11 · Xianshuai Shi, Jianfeng Zhu, Leibo Liu arxiv

This paper presents a gate-level Boolean evolutionary geometric attention neural network that models images as Boolean fields governed by logic gates. Each pixel is a Boolean variable (0 or 1) embedded on a two-dimension…

Boolean-aware Boolean Circuit Classification: A Comprehensive Study on Graph Neural Network

2024-11-13 · Liwei Ni, Xinquan Li, Biwei Xie, Huawei Li

Boolean circuit is a computational graph that consists of the dynamic directed graph structure and static functionality. The commonly used logic optimization and Boolean matching-based transformation can change the behav…

ClassificationGraph ClassificationGraph Neural Network