Object-centric proto-symbolic behavioural reasoning from pixels
Ruben van Bergen, Justus H\"ubotter, Alma Lago, Pablo Lanillos

TL;DR
This paper introduces a brain-inspired deep learning architecture that learns object-centric representations from pixels to enable reasoning and control in synthetic environments, bridging perception and high-level cognition without supervision.
Contribution
The work presents a novel architecture that learns object-based representations from raw pixels, facilitating logical reasoning and control in synthetic environments without supervision.
Findings
Agent learns emergent conditional behavioral reasoning.
Agent successfully performs logical composition and XOR operations.
Robustness to environmental changes and model violations.
Abstract
Autonomous intelligent agents must bridge computational challenges at disparate levels of abstraction, from the low-level spaces of sensory input and motor commands to the high-level domain of abstract reasoning and planning. A key question in designing such agents is how best to instantiate the representational space that will interface between these two levels -- ideally without requiring supervision in the form of expensive data annotations. These objectives can be efficiently achieved by representing the world in terms of objects (grounded in perception and action). In this work, we present a novel, brain-inspired, deep-learning architecture that learns from pixels to interpret, control, and reason about its environment, using object-centric representations. We show the utility of our approach through tasks in synthetic environments that require a combination of (high-level) logical…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsCognitive Science and Education Research · Language and cultural evolution · Psychiatry, Mental Health, Neuroscience
