Learning to Solve Abstract Reasoning Problems with Neurosymbolic Program Synthesis and Task Generation
The ability to think abstractly and reason by analogy is a prerequisite to rapidly adapt to new conditions, tackle newly encountered problems by decomposing them, and synthesize knowledge to solve problems comprehensively. We present TransCoder, a method for solving abstract problems based on neural program synthesis, and conduct a comprehensive analysis of decisions made by the generative module of the proposed architecture. At the core of TransCoder is a typed domain-specific language, designed to facilitate feature engineering and abstract reasoning. In training, we use the programs that failed to solve tasks to generate new tasks and gather them in a synthetic dataset. As each synthetic task created in this way has a known associated program (solution), the model is trained on them in supervised mode. Solutions are represented in a transparent programmatic form, which can be inspected and verified. We demonstrate TransCoder's performance using the Abstract Reasoning Corpus dataset, for which our framework generates tens of thousands of synthetic problems with corresponding solutions and facilitates systematic progress in learning.
Code (0)
등록된 구현이 없습니다.
Tasks
Feature EngineeringProgram SynthesisSimilar Papers 제목 키워드 기반
Lobster: A GPU-Accelerated Framework for Neurosymbolic Programming
Neurosymbolic programs combine deep learning with symbolic reasoning to achieve better data efficiency, interpretability, and generalizability compared to standalone deep learning approaches. However, existing neurosymbo…
GPUNeural networks for abstraction and reasoning: Towards broad generalization in machines
For half a century, artificial intelligence research has attempted to reproduce the human qualities of abstraction and reasoning - creating computer systems that can learn new concepts from a minimal set of examples, in …
ARCVisual ReasoningVector Symbolic Algebras for the Abstraction and Reasoning Corpus
The Abstraction and Reasoning Corpus for Artificial General Intelligence (ARC-AGI) is a generative, few-shot fluid intelligence benchmark. Although humans effortlessly solve ARC-AGI, it remains extremely difficult for ev…
Program SynthesisImproving Rule-based Reasoning in LLMs via Neurosymbolic Representations
Large language models (LLMs) continue to face challenges in reliably solving reasoning tasks, particularly tasks that involve precise rule following, as often found in mathematical reasoning tasks. This paper introduces …
Mathematical ReasoningBANSAI: Towards Bridging the AI Adoption Gap in Industrial Robotics with Neurosymbolic Programming
Over the past decade, deep learning helped solve manipulation problems across all domains of robotics. At the same time, industrial robots continue to be programmed overwhelmingly using traditional program representation…
Industrial RobotsProgram Synthesis