This paper presents a proof of concept for a novel evolutionary methodology inspired by core knowledge. This theory describes human cognition as a small set of innate abilities combined through compositionality. The proposed approach generates predictive descriptions of the interaction between elements in simple 2D videos. It exploits well-known strategies, such as image segmentation, object detection, simple laws of physics (kinematics and dynamics), and evolving rules, including high-level classes and their interactions. The experimental evaluation focuses on two classic video games, Pong and Arkanoid. Analyzing a small number of raw video frames, the methodology identifies objects, classes, and rules, creating a compact, high-level, predictive description of the interactions between the elements in the videos.

Towards an Evolutionary Approach for Exploting Core Knowledge in Artificial Intelligence / Calabrese, Andrea; Quer, Stefano; Squillero, Giovanni; Tonda, Alberto. - ELETTRONICO. - (2024), pp. 259-262. (Intervento presentato al convegno GECCO 2024: The Genetic and Evolutionary Computation Conference tenutosi a Melbourne, VIC (AUS) nel July 14 - 18, 2024) [10.1145/3638530.3654230].

Towards an Evolutionary Approach for Exploting Core Knowledge in Artificial Intelligence

Calabrese, Andrea;Quer, Stefano;Squillero, Giovanni;Tonda, Alberto
2024

Abstract

This paper presents a proof of concept for a novel evolutionary methodology inspired by core knowledge. This theory describes human cognition as a small set of innate abilities combined through compositionality. The proposed approach generates predictive descriptions of the interaction between elements in simple 2D videos. It exploits well-known strategies, such as image segmentation, object detection, simple laws of physics (kinematics and dynamics), and evolving rules, including high-level classes and their interactions. The experimental evaluation focuses on two classic video games, Pong and Arkanoid. Analyzing a small number of raw video frames, the methodology identifies objects, classes, and rules, creating a compact, high-level, predictive description of the interactions between the elements in the videos.
2024
979-8-4007-0495-6
File in questo prodotto:
File Dimensione Formato  
gecco_main.pdf

accesso aperto

Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: Pubblico - Tutti i diritti riservati
Dimensione 728.53 kB
Formato Adobe PDF
728.53 kB Adobe PDF Visualizza/Apri
3638530.3654230.pdf

accesso riservato

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 777.59 kB
Formato Adobe PDF
777.59 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2991108