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

Significance

Biological networks embody the capability to flexibly support a disparate variety of functions, learning with astonishing energy and sample efficiency. This motivates the search for biologically inspired learning rules for improving artificial intelligence. We propose a generation of bio-inspired networks composed of three-compartment neurons (inspired by L5 pyramidal neurons) and a paradigm for learning and computing. This generation of networks achieves properties that are inaccessible to standard networks, among which the capability to learn without error propagation, the possibility to robustly perform context-dependent tasks, and the possibility to implement hierarchical policies decomposing complex long-horizon tasks. Finally, we argue that our model is capable of accounting for context-dependent perceptive facilitation observed in humans and animals.

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 state-of-the-art performance in machine learning. Recent works have proposed that input segregation (neurons receive sensory information and higher-order feedback in segregated compartments), and nonlinear dendritic computation would support error backpropagation in biological neurons. However, these approaches require propagating errors with a fine spatiotemporal structure to all 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 target-based learning, which propagates targets rather than errors. A coincidence mechanism between the basal and the apical compartments allows for generating high-frequency bursts of spikes. This architecture supports 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 support for target-based learning. We show that this framework can be used to efficiently solve spatiotemporal tasks, such as context-dependent store and recall of three-dimensional trajectories, and navigation tasks. 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. We show a possible implementation of this in a two-level network, where the high network produces the contextual signal for the low network.