Local dendritic balance enables learning of efficient representations in networks of spiking neurons

TL;DR

This paper introduces a novel voltage-dependent synaptic plasticity scheme that enables neural networks of spiking neurons to learn efficient, high-dimensional representations through local dendritic balance, overcoming limitations of traditional Hebbian models.

Contribution

The study derives a new learning rule based on dendritic inhibition and voltage-dependent plasticity, demonstrating its robustness over Hebbian-like plasticity in complex input scenarios.

Findings

Dendritic inhibitory balance enables efficient representation learning.

Voltage-dependent plasticity outperforms Hebbian models with correlated inputs.

The proposed scheme is robust to inhibitory delays and complex input statistics.

Abstract

How can neural networks learn to efficiently represent complex and high-dimensional inputs via local plasticity mechanisms? Classical models of representation learning assume that input weights are learned via pairwise Hebbian-like plasticity. Here, we show that pairwise Hebbian-like plasticity only works under unrealistic requirements on neural dynamics and input statistics. To overcome these limitations, we derive from first principles a learning scheme based on voltage-dependent synaptic plasticity rules. Here, inhibition learns to locally balance excitatory input in individual dendritic compartments, and thereby can modulate excitatory synaptic plasticity to learn efficient representations. We demonstrate in simulations that this learning scheme works robustly even for complex, high-dimensional and correlated inputs, and with inhibitory transmission delays, where Hebbian-like plasticity fails. Our results draw a direct connection between dendritic excitatory-inhibitory balance and voltage-dependent synaptic plasticity as observed in vivo, and suggest that both are crucial for representation learning.