# System identification of neural systems: If we got it right, would we know?

arXiv: https://arxiv.org/abs/2302.06677 · HTML: https://mlsanity.com/paper/2302.06677/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 58 references that are in the map.
- First posted on arXiv 13 Feb 2023.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (2021)
- [Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet](https://mlsanity.com/paper/2101.11986/) (2021)
- [ResMLP: Feedforward networks for image classification with data-efficient training](https://mlsanity.com/paper/2105.03404/) (2021)
- [Insights on representational similarity in neural networks with canonical correlation](https://mlsanity.com/paper/1806.05759/) (2018)
- [On the Power and Limitations of Random Features for Understanding Neural Networks](https://mlsanity.com/paper/1904.00687/) (2019)
- [Brain-Like Object Recognition with High-Performing Shallow Recurrent ANNs](https://mlsanity.com/paper/1909.06161/) (2019)
- [Relating transformers to models and neural representations of the hippocampal formation](https://mlsanity.com/paper/2112.04035/) (2021)
- [Do You Even Need Attention? A Stack of Feed-Forward Layers Does Surprisingly Well on ImageNet](https://mlsanity.com/paper/2105.02723/) (2021)
- [Bridging the Gaps Between Residual Learning, Recurrent Neural Networks and Visual Cortex](https://mlsanity.com/paper/1604.03640/) (2016)
- [Grounding Representation Similarity with Statistical Testing](https://mlsanity.com/paper/2108.01661/) (2021)
- [The Algonauts Project 2021 Challenge: How the Human Brain Makes Sense of a World in Motion](https://mlsanity.com/paper/2104.13714/) (2021)
- [Joint rotational invariance and adversarial training of a dual-stream Transformer yields state of the art Brain-Score for Area V4](https://mlsanity.com/paper/2203.06649/) (2022)

## Built on by (most cited first, 9 of 9)

- [Evaluating Representational Similarity Measures from the Lens of Functional Correspondence](https://mlsanity.com/paper/2411.14633/) (2024)
- [AdaNCA: Neural Cellular Automata As Adaptors For More Robust Vision Transformer](https://mlsanity.com/paper/2406.08298/) (2024)
- [Training the Untrainable: Introducing Inductive Bias via Representational Alignment](https://mlsanity.com/paper/2410.20035/) (2024)
- [Estimating Neural Representation Alignment from Sparsely Sampled Inputs and Features](https://mlsanity.com/paper/2502.15104/) (2025)
- [Stimulus symmetries can confound representational similarity analyses](https://mlsanity.com/paper/2605.21324/) (2026)
- [Not all solutions are created equal: An analytical dissociation of functional and representational similarity in deep linear neural networks](https://mlsanity.com/paper/2609.38998/) (2026)
- [Network of Theseus (like the ship)](https://mlsanity.com/paper/2512.04198/) (2025)
- [Discovering Mechanistic Models of Neural Activity: System Identification in an in Silico Zebrafish](https://mlsanity.com/paper/2602.04492/) (2026)
- [The Umwelt Representation Hypothesis: Rethinking Universality](https://mlsanity.com/paper/2604.17960/) (2026)

## Abstract (arXiv)

Artificial neural networks are being proposed as models of parts of the brain. The networks are compared to recordings of biological neurons, and good performance in reproducing neural responses is considered to support the model's validity. A key question is how much this system identification approach tells us about brain computation. Does it validate one model architecture over another? We evaluate the most commonly used comparison techniques, such as a linear encoding model and centered kernel alignment, to correctly identify a model by replacing brain recordings with known ground truth models. System identification performance is quite variable; it also depends significantly on factors independent of the ground truth architecture, such as stimuli images. In addition, we show the limitations of using functional similarity scores in identifying higher-level architectural motifs.