SNN-Based Online Learning of Concepts and Action Laws in an Open World

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Grimaud, Christel, Longin, Dominique, Herzig, Andreas
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917048511102976
author Grimaud, Christel
Longin, Dominique
Herzig, Andreas
author_facet Grimaud, Christel
Longin, Dominique
Herzig, Andreas
contents We present the architecture of a fully autonomous, bio-inspired cognitive agent built around a spiking neural network (SNN) implementing the agent's semantic memory. This agent explores its universe and learns concepts of objects/situations and of its own actions in a one-shot manner. While object/situation concepts are unary, action concepts are triples made up of an initial situation, a motor activity, and an outcome. They embody the agent's knowledge of its universe's action laws. Both kinds of concepts have different degrees of generality. To make decisions the agent queries its semantic memory for the expected outcomes of envisaged actions and chooses the action to take on the basis of these predictions. Our experiments show that the agent handles new situations by appealing to previously learned general concepts and rapidly modifies its concepts to adapt to environment changes.
format Preprint
id arxiv_https___arxiv_org_abs_2411_12308
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SNN-Based Online Learning of Concepts and Action Laws in an Open World
Grimaud, Christel
Longin, Dominique
Herzig, Andreas
Artificial Intelligence
Machine Learning
Neural and Evolutionary Computing
Robotics
We present the architecture of a fully autonomous, bio-inspired cognitive agent built around a spiking neural network (SNN) implementing the agent's semantic memory. This agent explores its universe and learns concepts of objects/situations and of its own actions in a one-shot manner. While object/situation concepts are unary, action concepts are triples made up of an initial situation, a motor activity, and an outcome. They embody the agent's knowledge of its universe's action laws. Both kinds of concepts have different degrees of generality. To make decisions the agent queries its semantic memory for the expected outcomes of envisaged actions and chooses the action to take on the basis of these predictions. Our experiments show that the agent handles new situations by appealing to previously learned general concepts and rapidly modifies its concepts to adapt to environment changes.
title SNN-Based Online Learning of Concepts and Action Laws in an Open World
topic Artificial Intelligence
Machine Learning
Neural and Evolutionary Computing
Robotics
url https://arxiv.org/abs/2411.12308