Deep Sparse Coding for Invariant Multimodal Halle Berry Neurons

TL;DR

This paper introduces a biologically inspired deep sparse coding model with top-down feedback and lateral inhibition, leading to the emergence of multimodal invariant neurons similar to human Halle Berry neurons, outperforming standard CNNs.

Contribution

The work presents a novel deep sparse coding framework incorporating biologically inspired feedback mechanisms, resulting in emergent multimodal neurons and improved representation quality.

Findings

Emergence of Halle Berry-like neurons in the model

Superior qualitative and quantitative performance on vision tasks

Biologically inspired feedback enhances multimodal integration

Abstract

Deep feed-forward convolutional neural networks (CNNs) have become ubiquitous in virtually all machine learning and computer vision challenges; however, advancements in CNNs have arguably reached an engineering saturation point where incremental novelty results in minor performance gains. Although there is evidence that object classification has reached human levels on narrowly defined tasks, for general applications, the biological visual system is far superior to that of any computer. Research reveals there are numerous missing components in feed-forward deep neural networks that are critical in mammalian vision. The brain does not work solely in a feed-forward fashion, but rather all of the neurons are in competition with each other; neurons are integrating information in a bottom up and top down fashion and incorporating expectation and feedback in the modeling process. Furthermore, our visual cortex is working in tandem with our parietal lobe, integrating sensory information from various modalities. In our work, we sought to improve upon the standard feed-forward deep learning model by augmenting them with biologically inspired concepts of sparsity, top-down feedback, and lateral inhibition. We define our model as a sparse coding problem using hierarchical layers. We solve the sparse coding problem with an additional top-down feedback error driving the dynamics of the neural network. While building and observing the behavior of our model, we were fascinated that multimodal, invariant neurons naturally emerged that mimicked, "Halle Berry neurons" found in the human brain. Furthermore, our sparse representation of multimodal signals demonstrates qualitative and quantitative superiority to the standard feed-forward joint embedding in common vision and machine learning tasks.