BEAN: Interpretable Representation Learning with Biologically-Enhanced Artificial Neuronal Assembly Regularization
This addresses the issue of interpretability in AI for researchers and practitioners, though it is incremental as it builds on existing neuroscience-inspired methods.
The paper tackled the problem of uninterpretable representations in deep neural networks by proposing BEAN regularization, which models neuronal correlations inspired by biological assemblies, resulting in interpretable functional clusters and enhanced generalizability in few-shot learning without performance loss.
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.