Beyond spiking networks: the computational advantages of dendritic amplification and input segregation

TL;DR

This paper introduces a biologically inspired neuron model with dendritic compartments and burst mechanisms, enabling efficient, target-based learning for complex spatio-temporal tasks without error propagation.

Contribution

It proposes a novel three-compartment pyramidal neuron model supporting biologically plausible target-based learning, advancing AI capabilities inspired by neural structures.

Findings

The model efficiently solves spatio-temporal tasks like 3D trajectory recall.

It enables hierarchical imitation learning for complex decision-making.

The architecture supports burst-dependent learning rules based on dendritic input segregation.

Abstract

The brain can efficiently learn a wide range of tasks, motivating the search for biologically inspired learning rules for improving current artificial intelligence technology. Most biological models are composed of point neurons, and cannot achieve the state-of-the-art performances in machine learning. Recent works have proposed that segregation of dendritic input (neurons receive sensory information and higher-order feedback in segregated compartments) and generation of high-frequency bursts of spikes would support error backpropagation in biological neurons. However, these approaches require propagating errors with a fine spatio-temporal structure to the neurons, which is unlikely to be feasible in a biological network. To relax this assumption, we suggest that bursts and dendritic input segregation provide a natural support for biologically plausible target-based learning, which does not require error propagation. We propose a pyramidal neuron model composed of three separated compartments. A coincidence mechanism between the basal and the apical compartments allows for generating high-frequency bursts of spikes. This architecture allows for a burst-dependent learning rule, based on the comparison between the target bursting activity triggered by the teaching signal and the one caused by the recurrent connections, providing the support for target-based learning. We show that this framework can be used to efficiently solve spatio-temporal tasks, such as the store and recall of 3D trajectories. Finally, we suggest that this neuronal architecture naturally allows for orchestrating ``hierarchical imitation learning'', enabling the decomposition of challenging long-horizon decision-making tasks into simpler subtasks. This can be implemented in a two-level network, where the high-network acts as a ``manager'' and produces the contextual signal for the low-network, the ``worker''.