Out-of-Distribution Generalization under Augmented Stimuli Reveals the Inductive Bias of Visual Cortex Digital Twins

Ayumi Kasagi, Takemi Hieda, Yuki Hosaka, Ruixiang Li, Masato Taki, Teppei Matsui
Proceedings of the First Workshop on NeuroAI Multimodal Intelligence @ AAAI 2026, PMLR 308:10-17, 2026.

Abstract

An important goal in Neuro-AI is to develop a digital twin of the visual cortex. Currently, state-of-the-art models of the visual cortex require large amounts of training data, which are difficult to obtain for most neuroscience laboratories. Here, we propose an approach to alleviate this limitation by enhancing neuronal data quality through optimization of visual stimuli. We first evaluated various image-transformation methods in silico using CNN-based models of the mouse visual cortex. We then validated the selected methods in vivo using real mouse brain recordings. The in vivo experiments identified two methods that enhanced neuronal responses and accelerated the training of digital twins. Unexpectedly, one method (Sharpening) consistently failed to match the in silico predictions. This discrepancy was likely due to CNN’s inductive bias toward high spatial frequencies. Consistently, models of the visual cortex with more favorable spectral sensitivity successfully predicted in vivo neuronal responses to Sharpening-transformed images. Taken together, our work makes the following contributions toward the development of a digital twin of the visual cortex: 1) Two in vivo-validated image-transformation methods that enhance data quality and accelerate model training. 2) Evidence that the RNN-based model is more aligned with the real visual cortex than CNN- or ViT-based models.

Cite this Paper

BibTeX
@InProceedings{pmlr-v308-kasagi26a, title = {Out-of-Distribution Generalization under Augmented Stimuli Reveals the Inductive Bias of Visual Cortex Digital Twins}, author = {Kasagi, Ayumi and Hieda, Takemi and Hosaka, Yuki and Li, Ruixiang and Taki, Masato and Matsui, Teppei}, booktitle = {Proceedings of the First Workshop on NeuroAI Multimodal Intelligence @ AAAI 2026}, pages = {10--17}, year = {2026}, editor = {Abbasi-Asl, Reza and Iqbal, Asim and Ito, Shinya and Arkhipov, Anton and Sanborn, Sophia}, volume = {308}, series = {Proceedings of Machine Learning Research}, month = {27 Jan}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v308/main/assets/kasagi26a/kasagi26a.pdf}, url = {https://proceedings.mlr.press/v308/kasagi26a.html}, abstract = {An important goal in Neuro-AI is to develop a digital twin of the visual cortex. Currently, state-of-the-art models of the visual cortex require large amounts of training data, which are difficult to obtain for most neuroscience laboratories. Here, we propose an approach to alleviate this limitation by enhancing neuronal data quality through optimization of visual stimuli. We first evaluated various image-transformation methods in silico using CNN-based models of the mouse visual cortex. We then validated the selected methods in vivo using real mouse brain recordings. The in vivo experiments identified two methods that enhanced neuronal responses and accelerated the training of digital twins. Unexpectedly, one method (Sharpening) consistently failed to match the in silico predictions. This discrepancy was likely due to CNN’s inductive bias toward high spatial frequencies. Consistently, models of the visual cortex with more favorable spectral sensitivity successfully predicted in vivo neuronal responses to Sharpening-transformed images. Taken together, our work makes the following contributions toward the development of a digital twin of the visual cortex: 1) Two in vivo-validated image-transformation methods that enhance data quality and accelerate model training. 2) Evidence that the RNN-based model is more aligned with the real visual cortex than CNN- or ViT-based models.} }
Endnote
%0 Conference Paper %T Out-of-Distribution Generalization under Augmented Stimuli Reveals the Inductive Bias of Visual Cortex Digital Twins %A Ayumi Kasagi %A Takemi Hieda %A Yuki Hosaka %A Ruixiang Li %A Masato Taki %A Teppei Matsui %B Proceedings of the First Workshop on NeuroAI Multimodal Intelligence @ AAAI 2026 %C Proceedings of Machine Learning Research %D 2026 %E Reza Abbasi-Asl %E Asim Iqbal %E Shinya Ito %E Anton Arkhipov %E Sophia Sanborn %F pmlr-v308-kasagi26a %I PMLR %P 10--17 %U https://proceedings.mlr.press/v308/kasagi26a.html %V 308 %X An important goal in Neuro-AI is to develop a digital twin of the visual cortex. Currently, state-of-the-art models of the visual cortex require large amounts of training data, which are difficult to obtain for most neuroscience laboratories. Here, we propose an approach to alleviate this limitation by enhancing neuronal data quality through optimization of visual stimuli. We first evaluated various image-transformation methods in silico using CNN-based models of the mouse visual cortex. We then validated the selected methods in vivo using real mouse brain recordings. The in vivo experiments identified two methods that enhanced neuronal responses and accelerated the training of digital twins. Unexpectedly, one method (Sharpening) consistently failed to match the in silico predictions. This discrepancy was likely due to CNN’s inductive bias toward high spatial frequencies. Consistently, models of the visual cortex with more favorable spectral sensitivity successfully predicted in vivo neuronal responses to Sharpening-transformed images. Taken together, our work makes the following contributions toward the development of a digital twin of the visual cortex: 1) Two in vivo-validated image-transformation methods that enhance data quality and accelerate model training. 2) Evidence that the RNN-based model is more aligned with the real visual cortex than CNN- or ViT-based models.
APA
Kasagi, A., Hieda, T., Hosaka, Y., Li, R., Taki, M. & Matsui, T.. (2026). Out-of-Distribution Generalization under Augmented Stimuli Reveals the Inductive Bias of Visual Cortex Digital Twins. Proceedings of the First Workshop on NeuroAI Multimodal Intelligence @ AAAI 2026, in Proceedings of Machine Learning Research 308:10-17 Available from https://proceedings.mlr.press/v308/kasagi26a.html.

Related Material