Model-brain comparison using inter-animal transforms

2025-10-02

AI Summary

This study addresses the longstanding challenge in model–brain comparison of simultaneously achieving high predictive accuracy and mechanistic specificity. We propose a bidirectional mapping framework based on Inter-Subject Transformation Classes (IATC), which establishes invertible mappings between neural network model responses and cross-subject (human/mouse) brain activity, enabling models to be validated as “prototypical subjects.” To our knowledge, this is the first application of IATC to model–brain comparison. Integrated with Topological Deep Artificial Neural Networks (TDANNs), the framework disentangles visual system representations while preserving strong predictive performance and precisely resolving functional specificity across brain regions. Experimental results demonstrate that IATC substantially enhances model interpretability and explanatory power. By unifying mechanistic modeling with data-driven prediction, our approach introduces a novel paradigm for neuroscientifically grounded artificial intelligence.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Multimodal Learning
• Humans and AI: Brain-Sensing and Analysis

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Artificial neural network models have emerged as promising mechanistic models of the brain. However, there is little consensus on the correct method for comparing model activations to brain responses. Drawing on recent work in philosophy of neuroscience, we propose a comparison methodology based on the Inter-Animal Transform Class (IATC) - the strictest set of functions needed to accurately map neural responses between subjects in an animal population. Using the IATC, we can map bidirectionally between a candidate model's responses and brain data, assessing how well the model can masquerade as a typical subject using the same kinds of transforms needed to map across real subjects. We identify the IATC in three settings: a simulated population of neural network models, a population of mouse subjects, and a population of human subjects. We find that the IATC resolves detailed aspects of the neural mechanism, such as the non-linear activation function. Most importantly, we find that the IATC enables accurate predictions of neural activity while also achieving high specificity in mechanism identification, evidenced by its ability to separate response patterns from different brain areas while strongly aligning same-brain-area responses between subjects. In other words, the IATC is a proof-by-existence that there is no inherent tradeoff between the neural engineering goal of high model-brain predictivity and the neuroscientific goal of identifying mechanistically accurate brain models. Using IATC-guided transforms, we obtain new evidence in favor of topographical deep neural networks (TDANNs) as models of the visual system. Overall, the IATC enables principled model-brain comparisons, contextualizing previous findings about the predictive success of deep learning models of the brain, while improving upon previous approaches to model-brain comparison.

Problem

• Establishing principled methodology for comparing artificial neural network models to brain responses
• Resolving detailed neural mechanisms while maintaining high predictive accuracy for neural activity
• Enabling bidirectional mapping between model responses and brain data across different subject populations

Innovation

• Uses Inter-Animal Transform Class for model-brain mapping
• Bidirectional mapping between model responses and brain data
• Enables principled comparisons without predictive-accuracy tradeoff