# Unsupervised deep learning identifies semantic disentanglement in single inferotemporal neurons

arXiv: https://arxiv.org/abs/2006.14304 · HTML: https://mlsanity.com/paper/2006.14304/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jun 2020.

## Built on by (most cited first, 30 of 33)

- [Disentanglement with Biological Constraints: A Theory of Functional Cell Types](https://mlsanity.com/paper/2210.01768/) (2022)
- [Symmetry-Based Representations for Artificial and Biological General Intelligence](https://mlsanity.com/paper/2203.09250/) (2022)
- [A Closer Look at Benchmarking Self-Supervised Pre-training with Image Classification](https://mlsanity.com/paper/2407.12210/) (2024)
- [Representational dissimilarity metric spaces for stochastic neural networks](https://mlsanity.com/paper/2211.11665/) (2022)
- [Flow Factorized Representation Learning](https://mlsanity.com/paper/2309.13167/) (2023)
- [Robust Concept Erasure via Kernelized Rate-Distortion Maximization](https://mlsanity.com/paper/2312.00194/) (2023)
- [Poisson Variational Autoencoder](https://mlsanity.com/paper/2405.14473/) (2024)
- [Review of Disentanglement Approaches for Medical Applications -- Towards Solving the Gordian Knot of Generative Models in Healthcare](https://mlsanity.com/paper/2203.11132/) (2022)
- [Diversity vs. Recognizability: Human-like generalization in one-shot generative models](https://mlsanity.com/paper/2205.10370/) (2022)
- [Identifying Interpretable Visual Features in Artificial and Biological Neural Systems](https://mlsanity.com/paper/2310.11431/) (2023)
- [Supervised structure learning](https://mlsanity.com/paper/2311.10300/) (2023)
- [Neural population geometry and optimal coding of tasks with shared latent structure](https://mlsanity.com/paper/2402.16770/) (2024)
- [A Rubric for Human-like Agents and NeuroAI](https://mlsanity.com/paper/2212.04401/) (2022)
- [Latent Noise Segmentation: How Neural Noise Leads to the Emergence of Segmentation and Grouping](https://mlsanity.com/paper/2309.16515/) (2023)
- [Active Inference and Intentional Behaviour](https://mlsanity.com/paper/2312.07547/) (2023)
- [Disentangling Autoencoders (DAE)](https://mlsanity.com/paper/2202.09926/) (2022)
- [Active inference and artificial reasoning](https://mlsanity.com/paper/2512.21129/) (2025)
- [Top-down inference in an early visual cortex inspired hierarchical Variational Autoencoder](https://mlsanity.com/paper/2206.00436/) (2022)
- [Rotated Digit Recognition by Variational Autoencoders with Fixed Output Distributions](https://mlsanity.com/paper/2206.13388/) (2022)
- [Inferring response times of perceptual decisions with Poisson variational autoencoders](https://mlsanity.com/paper/2511.11480/) (2025)
- [Revisiting Disentanglement in Downstream Tasks: A Study on Its Necessity for Abstract Visual Reasoning](https://mlsanity.com/paper/2403.00352/) (2024)
- [Bridging Neuroscience and AI: Environmental Enrichment as a Model for Forward Knowledge Transfer](https://mlsanity.com/paper/2405.07295/) (2024)
- [How Video Meetings Change Your Expression](https://mlsanity.com/paper/2406.00955/) (2024)
- [Configural processing as an optimized strategy for robust object recognition in neural networks](https://mlsanity.com/paper/2407.19072/) (2024)
- [Leveraging a Cognitive Model to Measure Subjective Similarity of Human and GPT-4 Written Content](https://mlsanity.com/paper/2409.00269/) (2024)
- [Improving Unsupervised Task-driven Models of Ventral Visual Stream via Relative Position Predictivity](https://mlsanity.com/paper/2505.08316/) (2025)
- [Topoformer: brain-like topographic organization in Transformer language models through spatial querying and reweighting](https://mlsanity.com/paper/2510.18745/) (2025)
- [What does it mean to represent? Mental representations as falsifiable memory patterns](https://mlsanity.com/paper/2203.02956/) (2022)
- [Autodecompose: A generative self-supervised model for semantic decomposition](https://mlsanity.com/paper/2302.03124/) (2023)
- [Using Human-like Mechanism to Weaken Effect of Pre-training Weight Bias in Face-Recognition Convolutional Neural Network](https://mlsanity.com/paper/2310.13674/) (2023)

## Abstract (arXiv)

Deep supervised neural networks trained to classify objects have emerged as popular models of computation in the primate ventral stream. These models represent information with a high-dimensional distributed population code, implying that inferotemporal (IT) responses are also too complex to interpret at the single-neuron level. We challenge this view by modelling neural responses to faces in the macaque IT with a deep unsupervised generative model, beta-VAE. Unlike deep classifiers, beta-VAE "disentangles" sensory data into interpretable latent factors, such as gender or hair length. We found a remarkable correspondence between the generative factors discovered by the model and those coded by single IT neurons. Moreover, we were able to reconstruct face images using the signals from just a handful of cells. This suggests that the ventral visual stream may be optimising the disentangling objective, producing a neural code that is low-dimensional and semantically interpretable at the single-unit level.