Distinguishing representational geometries with controversial stimuli: Bayesian experimental design and its application to face dissimilarity judgments

11/28/2022
by   Tal Golan, et al.
0

Comparing representations of complex stimuli in neural network layers to human brain representations or behavioral judgments can guide model development. However, even qualitatively distinct neural network models often predict similar representational geometries of typical stimulus sets. We propose a Bayesian experimental design approach to synthesizing stimulus sets for adjudicating among representational models efficiently. We apply our method to discriminate among candidate neural network models of behavioral face dissimilarity judgments. Our results indicate that a neural network trained to invert a 3D-face-model graphics renderer is more human-aligned than the same architecture trained on identification, classification, or autoencoding. Our proposed stimulus synthesis objective is generally applicable to designing experiments to be analyzed by representational similarity analysis for model comparison.

READ FULL TEXT

page 13

page 14

research
06/08/2023

Actively learning a Bayesian matrix fusion model with deep side information

High-dimensional deep neural network representations of images and conce...
research
11/02/2022

Human alignment of neural network representations

Today's computer vision models achieve human or near-human level perform...
research
11/21/2019

Controversial stimuli: pitting neural networks against each other as models of human recognition

Distinct scientific theories can make similar predictions. To adjudicate...
research
10/18/2021

Comparing Deep Neural Nets with UMAP Tour

Neural networks should be interpretable to humans. In particular, there ...
research
09/21/2020

Learning Realistic Patterns from Unrealistic Stimuli: Generalization and Data Anonymization

Good training data is a prerequisite to develop useful ML applications. ...
research
11/13/2017

Modeling Human Categorization of Natural Images Using Deep Feature Representations

Over the last few decades, psychologists have developed sophisticated fo...
research
01/23/2018

Expectation Learning for Adaptive Crossmodal Stimuli Association

The human brain is able to learn, generalize, and predict crossmodal sti...

Please sign up or login with your details

Forgot password? Click here to reset