Optimal percentage of inhibitory synapses in multi-task learning

TL;DR

This paper investigates how a specific percentage of inhibitory synapses, around 30%, optimizes multi-task learning in neuronal networks by balancing excitability and resource variability, inspired by mammalian brain structures.

Contribution

It identifies the optimal inhibitory synapse percentage for multi-task learning, linking biological synapse ratios to network performance and information transmission efficiency.

Findings

30% inhibitory synapses optimize learning performance

Multi-task learning involves alternating learning and forgetting of rules

Optimal inhibitory percentage balances excitability and resource variability

Abstract

Performing more tasks in parallel is a typical feature of complex brains. These are characterized by the coexistence of excitatory and inhibitory synapses, whose percentage in mammals is measured to have a typical value of 20-30\%. Here we investigate parallel learning of more Boolean rules in neuronal networks. We find that multi-task learning results from the alternation of learning and forgetting of the individual rules. Interestingly, a fraction of 30\% inhibitory synapses optimizes the overall performance, carving a complex backbone supporting information transmission with a minimal shortest path length. We show that 30\% inhibitory synapses is the percentage maximizing the learning performance since it guarantees, at the same time, the network excitability necessary to express the response and the variability required to confine the employment of resources.