# BEAN: Interpretable Representation Learning with Biologically-Enhanced Artificial Neuronal Assembly Regularization

arXiv: https://arxiv.org/abs/1909.13698 · HTML: https://mlsanity.com/paper/1909.13698/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Sep 2019.

## Built on by (most cited first, 6 of 6)

- [Aligning Eyes between Humans and Deep Neural Network through Interactive Attention Alignment](https://mlsanity.com/paper/2202.02838/) (2022)
- [RES: A Robust Framework for Guiding Visual Explanation](https://mlsanity.com/paper/2206.13413/) (2022)
- [Schematic Memory Persistence and Transience for Efficient and Robust Continual Learning](https://mlsanity.com/paper/2105.02085/) (2021)
- [On "Deep Learning" Misconduct](https://mlsanity.com/paper/2211.16350/) (2022)
- [Post-Selections in AI and How to Avoid Them](https://mlsanity.com/paper/2106.13233/) (2021)
- [Misconduct in Post-Selections and Deep Learning](https://mlsanity.com/paper/2403.00773/) (2024)

## Abstract (arXiv)

Deep neural networks (DNNs) are known for extracting useful information from large amounts of data. However, the representations learned in DNNs are typically hard to interpret, especially in dense layers. One crucial issue of the classical DNN model such as multilayer perceptron (MLP) is that neurons in the same layer of DNNs are conditionally independent of each other, which makes co-training and emergence of higher modularity difficult. In contrast to DNNs, biological neurons in mammalian brains display substantial dependency patterns. Specifically, biological neural networks encode representations by so-called neuronal assemblies: groups of neurons interconnected by strong synaptic interactions and sharing joint semantic content. The resulting population coding is essential for human cognitive and mnemonic processes. Here, we propose a novel Biologically Enhanced Artificial Neuronal assembly (BEAN) regularization to model neuronal correlations and dependencies, inspired by cell assembly theory from neuroscience. Experimental results show that BEAN enables the formation of interpretable neuronal functional clusters and consequently promotes a sparse, memory/computation-efficient network without loss of model performance. Moreover, our few-shot learning experiments demonstrate that BEAN could also enhance the generalizability of the model when training samples are extremely limited.