City Research Online

AIGenC: AI generalisation via creativity

Cătărău-Cotuțiu, C., Mondragon, E. ORCID: 0000-0003-4180-1261 & Alonso, E. ORCID: 0000-0002-3306-695X (2022). AIGenC: AI generalisation via creativity. doi: 10.48550/arXiv.2205.09738


Inspired by cognitive theories of creativity, this paper introduces a computational model (AIGenC) that lays down the necessary components to enable artificial agents to learn, use and generate transferable representations. Unlike machine representation learning, which relies exclusively on raw sensory data, biological representations incorporate relational and associative information that embeds rich and structured concept spaces. The AIGenC model poses a hierarchical graph architecture with various levels and types of representations procured by different components. The first component, Concept Processing, extracts objects and affordances from sensory input and encodes them into a concept space. The resulting representations are stored in a dual memory system and enriched with goal-directed and temporal information acquired through reinforcement learning, creating a higher-level of abstraction. Two additional components work in parallel to detect and recover relevant concepts and create new ones, respectively, in a process akin to cognitive Reflective Reasoning and Blending. The Reflective Reasoning unit detects and recovers from memory concepts relevant to the task by means of a matching process that calculates a similarity value between the current state and memory graph structures. Once the matching interaction ends, rewards and temporal information are added to the graph, building further abstractions. If the reflective reasoning processing fails to offer a suitable solution, a blending operation comes into place, creating new concepts by combining past information. We discuss the model's capability to yield better out-of-distribution generalisation in artificial agents, thus advancing toward Artificial General Intelligence.

Publication Type: Other (Preprint)
Publisher Keywords: Affordances · Generalisation · Creativity · Representational Learning, Reinforcement Learning, Learning Transfer
Subjects: H Social Sciences > HM Sociology
H Social Sciences > HN Social history and conditions. Social problems. Social reform
Departments: School of Science & Technology > Computer Science
[thumbnail of Catarau_Mondragon_Alonso.pdf]
Text - Pre-print
Download (2MB) | Preview


Add to AnyAdd to TwitterAdd to FacebookAdd to LinkedinAdd to PinterestAdd to Email


Downloads per month over past year

View more statistics

Actions (login required)

Admin Login Admin Login