Learning to combine top-down context and feed-forward representations under ambiguity with apical and basal dendrites

TL;DR

This paper introduces a biologically inspired neural network architecture with distinct apical and basal compartments, enabling better contextual and sensory integration under ambiguity, outperforming models without this feature.

Contribution

It demonstrates how apical and basal dendrite-inspired compartments can be integrated in neural networks to improve contextual processing in ambiguous scenarios.

Findings

Model outperforms non-apical prior models when context contradicts sensory data.

Successfully learns to select appropriate integration strategies across diverse scenarios.

Proposes a new multi-scenario contextual integration task with generative image modeling.

Abstract

One of the hallmark features of neocortical anatomy is the presence of extensive top-down projections into primary sensory areas, with many impinging on the distal apical dendrites of pyramidal neurons. While it is known that they exert a modulatory effect, altering the gain of responses, their functional role remains an active area of research. It is hypothesized that these top-down projections carry contextual information that can help animals to resolve ambiguities in sensory data. One proposed mechanism of contextual integration is a non-linear integration of distinct input streams at apical and basal dendrites of pyramidal neurons. Computationally, however, it is yet to be demonstrated how such an architecture could leverage distinct compartments for flexible contextual integration and sensory processing when both sensory and context signals can be unreliable. Here, we implement an augmented deep neural network with distinct apical and basal compartments that integrates a) contextual information from top-down projections to apical compartments, and b) sensory representations driven by bottom-up projections to basal compartments, via a biophysically inspired rule. In addition, we develop a new multi-scenario contextual integration task using a generative image modeling approach. In addition to generalizing previous contextual integration tasks, it better captures the diversity of scenarios where neither contextual nor sensory information are fully reliable. To solve this task, this model successfully learns to select among integration strategies. We find that our model outperforms those without the "apical prior" when contextual information contradicts sensory input. Altogether, this suggests that the apical prior and biophysically inspired integration rule could be key components necessary for handling the ambiguities that animals encounter in the diverse contexts of the real world.