Saved in:
Bibliographic Details
Main Authors: Goldowsky, Howard, Sarathy, Vasanth
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.08684
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929589685583872
author Goldowsky, Howard
Sarathy, Vasanth
author_facet Goldowsky, Howard
Sarathy, Vasanth
contents We propose an approach to analogical inference that marries the neuro-symbolic computational power of complex-sampled hyperdimensional computing (HDC) with Conceptual Spaces Theory (CST), a promising theory of semantic meaning. CST sketches, at an abstract level, approaches to analogical inference that go beyond the standard predicate-based structure mapping theories. But it does not describe how such an approach can be operationalized. We propose a concrete HDC-based architecture that computes several types of analogy classified by CST. We present preliminary proof-of-concept experimental results within a toy domain and describe how it can perform category-based and property-based analogical reasoning.
format Preprint
id arxiv_https___arxiv_org_abs_2411_08684
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Analogical Reasoning Within a Conceptual Hyperspace
Goldowsky, Howard
Sarathy, Vasanth
Artificial Intelligence
We propose an approach to analogical inference that marries the neuro-symbolic computational power of complex-sampled hyperdimensional computing (HDC) with Conceptual Spaces Theory (CST), a promising theory of semantic meaning. CST sketches, at an abstract level, approaches to analogical inference that go beyond the standard predicate-based structure mapping theories. But it does not describe how such an approach can be operationalized. We propose a concrete HDC-based architecture that computes several types of analogy classified by CST. We present preliminary proof-of-concept experimental results within a toy domain and describe how it can perform category-based and property-based analogical reasoning.
title Analogical Reasoning Within a Conceptual Hyperspace
topic Artificial Intelligence
url https://arxiv.org/abs/2411.08684