Saved in:
Bibliographic Details
Main Authors: Alam, Mohammad Mahmudul, Oberle, Alexander, Raff, Edward, Biderman, Stella, Oates, Tim, Holt, James
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.22669
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910678274539520
author Alam, Mohammad Mahmudul
Oberle, Alexander
Raff, Edward
Biderman, Stella
Oates, Tim
Holt, James
author_facet Alam, Mohammad Mahmudul
Oberle, Alexander
Raff, Edward
Biderman, Stella
Oates, Tim
Holt, James
contents Vector Symbolic Architectures (VSAs) are one approach to developing Neuro-symbolic AI, where two vectors in $\mathbb{R}^d$ are `bound' together to produce a new vector in the same space. VSAs support the commutativity and associativity of this binding operation, along with an inverse operation, allowing one to construct symbolic-style manipulations over real-valued vectors. Most VSAs were developed before deep learning and automatic differentiation became popular and instead focused on efficacy in hand-designed systems. In this work, we introduce the Hadamard-derived linear Binding (HLB), which is designed to have favorable computational efficiency, and efficacy in classic VSA tasks, and perform well in differentiable systems. Code is available at https://github.com/FutureComputing4AI/Hadamard-derived-Linear-Binding
format Preprint
id arxiv_https___arxiv_org_abs_2410_22669
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Walsh Hadamard Derived Linear Vector Symbolic Architecture
Alam, Mohammad Mahmudul
Oberle, Alexander
Raff, Edward
Biderman, Stella
Oates, Tim
Holt, James
Artificial Intelligence
Machine Learning
Vector Symbolic Architectures (VSAs) are one approach to developing Neuro-symbolic AI, where two vectors in $\mathbb{R}^d$ are `bound' together to produce a new vector in the same space. VSAs support the commutativity and associativity of this binding operation, along with an inverse operation, allowing one to construct symbolic-style manipulations over real-valued vectors. Most VSAs were developed before deep learning and automatic differentiation became popular and instead focused on efficacy in hand-designed systems. In this work, we introduce the Hadamard-derived linear Binding (HLB), which is designed to have favorable computational efficiency, and efficacy in classic VSA tasks, and perform well in differentiable systems. Code is available at https://github.com/FutureComputing4AI/Hadamard-derived-Linear-Binding
title A Walsh Hadamard Derived Linear Vector Symbolic Architecture
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2410.22669