Untrained neural networks can demonstrate memorization-independent abstract reasoning.

ABSTRACT: The nature of abstract reasoning is a matter of debate. Modern artificial neural network (ANN) models, like large language models, demonstrate impressive success when tested on abstract reasoning problems. However, it has been argued that their success reflects some form of memorization of similar problems (data contamination) rather than a general-purpose abstract reasoning capability. This concern is supported by evidence of brittleness, and the requirement of extensive training. In our study, we explored whether abstract reasoning can be achieved using the toolbox of ANNs, without prior training. Specifically, we studied an ANN model in which the weights of a naive network are optimized during the solution of the problem, using the problem data itself, rather than any prior knowledge. W

SUBMITTER: Barak T 

PROVIDER: S-EPMC11549345 | biostudies-literature | 2024 Nov

REPOSITORIES: biostudies-literature