Examining Reject Relations in Stimulus Equivalence Simulations

TL;DR

This study investigates how reject relations affect stimulus equivalence simulations using neural network models, revealing that these models may rely on associative learning rather than true equivalence class formation.

Contribution

It provides a comparative analysis of neural networks and probabilistic models in stimulus equivalence, highlighting the influence of reject relations on performance.

Findings

Reject relations impact agent performance.

Neural networks often perform similarly to associative models.

Reject relations and biased comparisons can lead to high accuracy without true equivalence.

Abstract

Simulations offer a valuable tool for exploring stimulus equivalence (SE), yet the potential of reject relations to disrupt the assessment of equivalence class formation is contentious. This study investigates the role of reject relations in the acquisition of stimulus equivalence using computational models. We examined feedforward neural networks (FFNs), bidirectional encoder representations from transformers (BERT), and generative pre-trained transformers (GPT) across 18 conditions in matching-to-sample (MTS) simulations. Conditions varied in training structure (linear series, one-to-many, and many-to-one), relation type (select-only, reject-only, and select-reject), and negative comparison selection (standard and biased). A probabilistic agent served as a benchmark, embodying purely associative learning. The primary goal was to determine whether artificial neural networks could demonstrate equivalence class formation or whether their performance reflected associative learning. Results showed that reject relations influenced agent performance. While some agents achieved high accuracy on equivalence tests, particularly with reject relations and biased negative comparisons, this performance was comparable to the probabilistic agent. These findings suggest that artificial neural networks, including transformer models, may rely on associative strategies rather than SE. This underscores the need for careful consideration of reject relations and more stringent criteria in computational models of equivalence.