# Optimal percentage of inhibitory synapses in multi-task learning

arXiv: https://arxiv.org/abs/1508.05707 · HTML: https://mlsanity.com/paper/1508.05707/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Aug 2015.

## Built on by (most cited first, 1 of 1)

- [Spontaneous Emergence of Computation in Network Cascades](https://mlsanity.com/paper/2204.11956/) (2022)

## Abstract (arXiv)

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.