Brain-like Flexible Visual Inference by Harnessing Feedback-Feedforward Alignment

TL;DR

This paper introduces Feedback-Feedforward Alignment (FFA), a biologically plausible learning algorithm that enables feedback pathways to support flexible visual inference functions like denoising and hallucination by aligning with feedforward pathways.

Contribution

The paper proposes FFA, a novel co-optimization algorithm that aligns feedback and feedforward pathways, supporting flexible visual inference and improving biological plausibility over traditional methods.

Findings

FFA successfully co-optimizes classification and reconstruction tasks.

Feedback pathways develop emergent visual inference functions.

FFA is more bio-plausible than backpropagation.

Abstract

In natural vision, feedback connections support versatile visual inference capabilities such as making sense of the occluded or noisy bottom-up sensory information or mediating pure top-down processes such as imagination. However, the mechanisms by which the feedback pathway learns to give rise to these capabilities flexibly are not clear. We propose that top-down effects emerge through alignment between feedforward and feedback pathways, each optimizing its own objectives. To achieve this co-optimization, we introduce Feedback-Feedforward Alignment (FFA), a learning algorithm that leverages feedback and feedforward pathways as mutual credit assignment computational graphs, enabling alignment. In our study, we demonstrate the effectiveness of FFA in co-optimizing classification and reconstruction tasks on widely used MNIST and CIFAR10 datasets. Notably, the alignment mechanism in FFA endows feedback connections with emergent visual inference functions, including denoising, resolving occlusions, hallucination, and imagination. Moreover, FFA offers bio-plausibility compared to traditional backpropagation (BP) methods in implementation. By repurposing the computational graph of credit assignment into a goal-driven feedback pathway, FFA alleviates weight transport problems encountered in BP, enhancing the bio-plausibility of the learning algorithm. Our study presents FFA as a promising proof-of-concept for the mechanisms underlying how feedback connections in the visual cortex support flexible visual functions. This work also contributes to the broader field of visual inference underlying perceptual phenomena and has implications for developing more biologically inspired learning algorithms.