# Explaining V1 Properties with a Biologically Constrained Deep Learning Architecture

arXiv: https://arxiv.org/abs/2305.11275 · HTML: https://mlsanity.com/paper/2305.11275/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 62 references that are in the map.
- First posted on arXiv 18 May 2023.

## Builds on (most cited first, 17 of 17)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [Adversarial Training for Free!](https://mlsanity.com/paper/1904.12843/) (2019)
- [Polar Transformer Networks](https://mlsanity.com/paper/1709.01889/) (2017)
- [Toward Next-Generation Artificial Intelligence: Catalyzing the NeuroAI Revolution](https://mlsanity.com/paper/2210.08340/) (2022)
- [Learning From Brains How to Regularize Machines](https://mlsanity.com/paper/1911.05072/) (2019)
- [Biologically Inspired Mechanisms for Adversarial Robustness](https://mlsanity.com/paper/2006.16427/) (2020)
- [Towards robust vision by multi-task learning on monkey visual cortex](https://mlsanity.com/paper/2107.14344/) (2021)
- [Warped Convolutions: Efficient Invariance to Spatial Transformations](https://mlsanity.com/paper/1609.04382/) (2016)
- [On-Off Center-Surround Receptive Fields for Accurate and Robust Image Classification](https://mlsanity.com/paper/2106.07091/) (2021)
- [Towards Biologically Plausible Convolutional Networks](https://mlsanity.com/paper/2106.13031/) (2021)
- [Recurrent Attention Model with Log-Polar Mapping is Robust against Adversarial Attacks](https://mlsanity.com/paper/2002.05388/) (2020)

## Built on by (most cited first, 4 of 4)

- [BRACTIVE: A Brain Activation Approach to Human Visual Brain Learning](https://mlsanity.com/paper/2405.18808/) (2024)
- [Brainformer: Mimic Human Visual Brain Functions to Machine Vision Models via fMRI](https://mlsanity.com/paper/2312.00236/) (2023)
- [Modeling Dynamic Neural Activity by combining Naturalistic Video Stimuli and Stimulus-independent Latent Factors](https://mlsanity.com/paper/2410.16136/) (2024)
- [Self-Attention-Based Contextual Modulation Improves Neural System Identification](https://mlsanity.com/paper/2406.07843/) (2024)

## Abstract (arXiv)

Convolutional neural networks (CNNs) have recently emerged as promising models of the ventral visual stream, despite their lack of biological specificity. While current state-of-the-art models of the primary visual cortex (V1) have surfaced from training with adversarial examples and extensively augmented data, these models are still unable to explain key neural properties observed in V1 that arise from biological circuitry. To address this gap, we systematically incorporated neuroscience-derived architectural components into CNNs to identify a set of mechanisms and architectures that comprehensively explain neural activity in V1. We show drastic improvements in model-V1 alignment driven by the integration of architectural components that simulate center-surround antagonism, local receptive fields, tuned normalization, and cortical magnification. Upon enhancing task-driven CNNs with a collection of these specialized components, we uncover models with latent representations that yield state-of-the-art explanation of V1 neural activity and tuning properties. Our results highlight an important advancement in the field of NeuroAI, as we systematically establish a set of architectural components that contribute to unprecedented explanation of V1. The neuroscience insights that could be gleaned from increasingly accurate in-silico models of the brain have the potential to greatly advance the fields of both neuroscience and artificial intelligence.