A Neurodiversity-Inspired Solver for the Abstraction \& Reasoning Corpus (ARC) Using Visual Imagery and Program Synthesis

• URL: http://arxiv.org/abs/2302.09425v3
• Date: Tue, 31 Oct 2023 18:05:28 GMT
• Title: A Neurodiversity-Inspired Solver for the Abstraction \& Reasoning Corpus (ARC) Using Visual Imagery and Program Synthesis
• Authors: James Ainooson, Deepayan Sanyal, Joel P. Michelson, Yuan Yang, Maithilee Kunda
• Abstract summary: We propose a new AI approach to core knowledge that combines visual representations of core knowledge inspired by human mental imagery abilities. We demonstrate our system's performance on the very difficult Abstraction & Reasoning (ARC) challenge. We share experimental results from publicly available ARC items as well as from our 4th-place finish on the private test set during the 2022 global ARCathon challenge.
• Score: 6.593059418464748
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Core knowledge about physical objects -- e.g., their permanency, spatial transformations, and interactions -- is one of the most fundamental building blocks of biological intelligence across humans and non-human animals. While AI techniques in certain domains (e.g. vision, NLP) have advanced dramatically in recent years, no current AI systems can yet match human abilities in flexibly applying core knowledge to solve novel tasks. We propose a new AI approach to core knowledge that combines 1) visual representations of core knowledge inspired by human mental imagery abilities, especially as observed in studies of neurodivergent individuals; with 2) tree-search-based program synthesis for flexibly combining core knowledge to form new reasoning strategies on the fly. We demonstrate our system's performance on the very difficult Abstraction \& Reasoning Corpus (ARC) challenge, and we share experimental results from publicly available ARC items as well as from our 4th-place finish on the private test set during the 2022 global ARCathon challenge.

Related papers

• Aligning Generalisation Between Humans and Machines [74.120848518198]
  Recent advances in AI have resulted in technology that can support humans in scientific discovery and decision support but may also disrupt democracies and target individuals. The responsible use of AI increasingly shows the need for human-AI teaming. A crucial yet often overlooked aspect of these interactions is the different ways in which humans and machines generalise.
  arXiv  Detail & Related papers  (2024-11-23T18:36:07Z)
• Brain-like Functional Organization within Large Language Models [58.93629121400745]
  The human brain has long inspired the pursuit of artificial intelligence (AI) Recent neuroimaging studies provide compelling evidence of alignment between the computational representation of artificial neural networks (ANNs) and the neural responses of the human brain to stimuli. In this study, we bridge this gap by directly coupling sub-groups of artificial neurons with functional brain networks (FBNs) This framework links the AN sub-groups to FBNs, enabling the delineation of brain-like functional organization within large language models (LLMs)
  arXiv  Detail & Related papers  (2024-10-25T13:15:17Z)
• A Neuro-mimetic Realization of the Common Model of Cognition via Hebbian Learning and Free Energy Minimization [55.11642177631929]
  Large neural generative models are capable of synthesizing semantically rich passages of text or producing complex images. We discuss the COGnitive Neural GENerative system, such an architecture that casts the Common Model of Cognition.
  arXiv  Detail & Related papers  (2023-10-14T23:28:48Z)
• Advancing Perception in Artificial Intelligence through Principles of Cognitive Science [6.637438611344584]
  We focus on the cognitive functions of perception, which is the process of taking signals from one's surroundings as input, and processing them to understand the environment. We present a collection of methods in AI for researchers to build AI systems inspired by cognitive science.
  arXiv  Detail & Related papers  (2023-10-13T01:21:55Z)
• Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems [268.585904751315]
  New area of research known as AI for science (AI4Science) Areas aim at understanding the physical world from subatomic (wavefunctions and electron density), atomic (molecules, proteins, materials, and interactions), to macro (fluids, climate, and subsurface) scales. Key common challenge is how to capture physics first principles, especially symmetries, in natural systems by deep learning methods.
  arXiv  Detail & Related papers  (2023-07-17T12:14:14Z)
• Incremental procedural and sensorimotor learning in cognitive humanoid robots [52.77024349608834]
  This work presents a cognitive agent that can learn procedures incrementally. We show the cognitive functions required in each substage and how adding new functions helps address tasks previously unsolved by the agent. Results show that this approach is capable of solving complex tasks incrementally.
  arXiv  Detail & Related papers  (2023-04-30T22:51:31Z)
• BO-Muse: A human expert and AI teaming framework for accelerated experimental design [58.61002520273518]
  Our algorithm lets the human expert take the lead in the experimental process. We show that our algorithm converges sub-linearly, at a rate faster than the AI or human alone.
  arXiv  Detail & Related papers  (2023-03-03T02:56:05Z)
• The Algonauts Project 2023 Challenge: How the Human Brain Makes Sense of Natural Scenes [0.0]
  We introduce the 2023 installment of the Algonauts Project challenge: How the Human Brain Makes Sense of Natural Scenes. This installment prompts the fields of artificial and biological intelligence to come together towards building computational models of the visual brain. The challenge is open to all and makes results directly comparable and transparent through a public leaderboard automatically updated after each submission.
  arXiv  Detail & Related papers  (2023-01-09T08:27:36Z)
• The Ninth Advances in Cognitive Systems (ACS) Conference [3.7706789983985303]
  ACS is an annual meeting for research on the initial goals of artificial intelligence and cognitive science. It aims to explain the mind in computational terms and to reproduce the entire range of human cognitive abilities in computational artifacts.
  arXiv  Detail & Related papers  (2022-01-16T20:57:08Z)
• Learning as Reinforcement: Applying Principles of Neuroscience for More General Reinforcement Learning Agents [1.0742675209112622]
  We implement an architecture founded in principles of experimental neuroscience, by combining computationally efficient abstractions of biological algorithms. Our approach is inspired by research on spike-timing dependent plasticity, the transition between short and long term memory, and the role of various neurotransmitters in rewarding curiosity. The Neurons-in-a-Box architecture can learn in a wholly generalizable manner, and demonstrates an efficient way to build and apply representations without explicitly optimizing over a set of criteria or actions.
  arXiv  Detail & Related papers  (2020-04-20T04:06:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.