# Relating CNNs with brain: Challenges and findings

arXiv: https://arxiv.org/abs/2108.09768 · HTML: https://mlsanity.com/paper/2108.09768/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 18 references that are in the map.
- First posted on arXiv 22 Aug 2021.

## Builds on (most cited first, 6 of 6)

- [Billion-scale semi-supervised learning for image classification](https://mlsanity.com/paper/1905.00546/) (2019)
- [Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Brain's Ventral Visual Pathway](https://mlsanity.com/paper/1411.6422/) (2014)
- [The Algonauts Project 2021 Challenge: How the Human Brain Makes Sense of a World in Motion](https://mlsanity.com/paper/2104.13714/) (2021)
- [Pixels to Voxels: Modeling Visual Representation in the Human Brain](https://mlsanity.com/paper/1407.5104/) (2014)
- [A visual encoding model based on deep neural networks and transfer learning](https://mlsanity.com/paper/1902.08793/) (2019)
- [Effective and efficient ROI-wise visual encoding using an end-to-end CNN regression model and selective optimization](https://mlsanity.com/paper/1907.11885/) (2019)

## Built on by (most cited first, 3 of 3)

- [Adaptive Federated Pruning in Hierarchical Wireless Networks](https://mlsanity.com/paper/2305.09042/) (2023)
- [A Privacy-Preserving Outsourced Data Model in Cloud Environment](https://mlsanity.com/paper/2211.13542/) (2022)
- [A Hybrid Proactive And Predictive Framework For Edge Cloud Resource Management](https://mlsanity.com/paper/2511.16075/) (2025)

## Abstract (arXiv)

Conventional neural network models (CNN), loosely inspired by the primate visual system, have been shown to predict neural responses in the visual cortex. However, the relationship between CNNs and the visual system is incomplete due to many reasons. On one hand state of the art CNN architecture is very complex, yet can be fooled by imperceptibly small, explicitly crafted perturbations which makes it hard difficult to map layers of the network with the visual system and to understand what they are doing. On the other hand, we don't know the exact mapping between feature space of the CNNs and the space domain of the visual cortex, which makes it hard to accurately predict neural responses. In this paper we review the challenges and the methods that have been used to predict neural responses in the visual cortex and whole brain as part of The Algonauts Project 2021 Challenge: "How the Human Brain Makes Sense of a World in Motion".