A neuro-inspired computational model of life-long learning and catastrophic interference, mimicking hippocampus novelty-based dopamine modulation and lateral inhibitory plasticity.

Abstract

The human brain has a remarkable lifelong learning capability to acquire new experiences while retaining previously acquired information. Several hypotheses have been proposed to explain this capability, but the underlying mechanisms are still unclear. Here, we propose a neuro-inspired firing-rate computational model involving the hippocampus and surrounding areas, that encompasses two key mechanisms possibly underlying this capability. The first is based on signals encoded by the neuromodulator dopamine, which is released by novel stimuli and enhances plasticity only when needed. The second is based on a homeostatic plasticity mechanism that involves the lateral inhibitory connections of the pyramidal neurons of the hippocampus. These mechanisms tend to protect neurons that have already been heavily employed in encoding previous experiences. The model was tested with images from the MNIST machine learning dataset, and with more naturalistic images, for its ability to mitigate catastrophic interference in lifelong learning. The results show that the proposed biologically grounded mechanisms can effectively enhance the learning of new stimuli while protecting previously acquired knowledge. The proposed mechanisms could be investigated in future empirical animal experiments and inspire machine learning models.