Guiding Sparse Neural Networks with Neurobiological Principles to Elicit Biologically Plausible Representations
This work addresses the challenge of improving neural network efficiency and adaptability for AI researchers, though it appears incremental by building on existing neurobiological inspirations.
The paper tackled the problem of deep neural networks' poor generalization and few-shot learning by integrating neurobiological principles like sparsity and Dale's law, resulting in enhanced robustness against adversarial attacks and superior generalization in few-shot scenarios.
While deep neural networks (DNNs) have achieved remarkable performance in tasks such as image recognition, they often struggle with generalization, learning from few examples, and continuous adaptation - abilities inherent in biological neural systems. These challenges arise due to DNNs' failure to emulate the efficient, adaptive learning mechanisms of biological networks. To address these issues, we explore the integration of neurobiologically inspired assumptions in neural network learning. This study introduces a biologically inspired learning rule that naturally integrates neurobiological principles, including sparsity, lognormal weight distributions, and adherence to Dale's law, without requiring explicit enforcement. By aligning with these core neurobiological principles, our model enhances robustness against adversarial attacks and demonstrates superior generalization, particularly in few-shot learning scenarios. Notably, integrating these constraints leads to the emergence of biologically plausible neural representations, underscoring the efficacy of incorporating neurobiological assumptions into neural network design. Preliminary results suggest that this approach could extend from feature-specific to task-specific encoding, potentially offering insights into neural resource allocation for complex tasks.