Descrizione del progetto
Un nuovo modo di dare una coscienza all’IA
La creazione della coscienza è una delle sfide più importanti nel campo dell’IA, che è progredito rapidamente nell’ultimo decennio. C’è ancora molta strada da fare prima che le macchine possano eguagliare le capacità umane nella coscienza e nella cognizione sociale. Il progetto ASTOUND, finanziato dall’UE, mira a formare una coscienza nelle macchine. L’architettura IA del progetto per la coscienza artificiale si basa sulla teoria degli schemi di attenzione. Suggerisce che il cervello costruisce la consapevolezza soggettiva come un modello schematico di attenzione e che le macchine possono attribuire le proprietà della coscienza ad altri in modo simile. Nel complesso, ASTOUND intende creare un agente conversazionale virtuale in grado di comprendere il linguaggio naturale con maggiore precisione e di prendere decisioni empatiche.
Obiettivo
In the last decade, deep learning algorithms have enabled AI systems to perform a series of tasks, like speech and image recognition, as well as or better than humans. However, this technology is not going to be enough to deliver human-level intelligence without consciousness. Without understanding the subjective awareness element, it may be impossible to build AI that has a human-like ability to focus its computational resources and intelligently control that focus and interact with people in a socially competent manner. ASTOUND proposes an Integrative Approach For Awareness Engineering to establish consciousness in machines. The approach consists of an AI architecture for Artificial Consciousness based on the Attention Schema Theory (AST), a novel approach to social cognition that reconciles some of the current most debated cognitive neuroscience theories of consciousness. According to the AST, the brain constructs subjective awareness as a schematic model of the process of attention, suggesting that an information-processing machine could attribute consciousness properties to others in a similar way. The AST-based architecture proposed by ASTOUND will combine an Attention Mechanism provided by the attentional layers in a deep neural architecture and a Long Term Memory module allowing interplay between internal and external stimuli (data) with an Attention Schema that will determine empathic and trustworthy decision-making. ASTOUND will first implement this architecture into a virtual conversational agent (i.e. chatbot) to verify the hypothesis that an artificial consciousness based on AST will improve performance in a task of natural language understanding. ASTOUND will provide insights into consciousness that are concrete enough, and mechanistic enough, that engineers can build upon it to facilitate future technologies. The study has the potential to be a toolbox for the construction of an EIC Portfolio in conscious AI.
Campo scientifico
Parole chiave
Programma(i)
- HORIZON.3.1 - The European Innovation Council (EIC) Main Programme
Invito a presentare proposte
HORIZON-EIC-2021-PATHFINDERCHALLENGES-01
Vedi altri progetti per questo bandoMeccanismo di finanziamento
HORIZON-EIC - HORIZON EIC GrantsCoordinatore
28040 Madrid
Spagna