Article

Neural networks for abstraction and reasoning: Towards broad generalization in machines

2024-04-30

Abstract excerpt

<title>Abstract</title> <p>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 settings where humans find this easy. While specific neural networks are able to solve an impressive range of problems, broad generalisation to situations outside their...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 15d5c438-0415-5870-b405-5beba7c291ca
DOI: 10.21203/rs.3.rs-4296928/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Neural networks for abstraction and reasoning: Towards broad generalization in machinesDOI 10.21203/rs.3.rs-4296928/v1Read

GradLIME: A CNN Local Interpretation Model Based on Feature Gradient ActivationSemantic proximity Read

Advancing Abstract Reasoning for RPMs with a Path Aggregation Network and Deep Predictive ReasoningSemantic proximity Read

VPNet: A Unified Explainable Classification Framework Using Probabilistic Circuits and Foundation ModelsSemantic proximity Read

From photos to sketches - how humans and deep neural networks process objects across different levels of visual abstractionSemantic proximity Read

Interpretable Reasoning in Large Language Models: A Neurosymbolic ApproachSemantic proximity Read

The Generalization Artist - Or: How Can We Characterize Human Generalization?Semantic proximity Read

Learning Representations by Humans, for HumansSemantic proximity Read

CogNGen: Constructing the kernel of a hyperdimensional predictive processing cognitive architectureSemantic proximity Read

Constrained Object Hierarchies as a Unified Theoretical Model for Intelligence and Intelligent SystemsSemantic proximity Read

BMRS: Bongard–Maximov Problems for Remote SensingSemantic proximity Read

Leveraging prior concept learning improves ability to generalize from few examples in computational models of human object recognitionSemantic proximity Read

Abstraction, Validation, and Generalization for Explainable Artificial IntelligenceSemantic proximity Read