Towards Biologically Plausible Convolutional Networks

by   Roman Pogodin, et al.

Convolutional networks are ubiquitous in deep learning. They are particularly useful for images, as they reduce the number of parameters, reduce training time, and increase accuracy. However, as a model of the brain they are seriously problematic, since they require weight sharing - something real neurons simply cannot do. Consequently, while neurons in the brain can be locally connected (one of the features of convolutional networks), they cannot be convolutional. Locally connected but non-convolutional networks, however, significantly underperform convolutional ones. This is troublesome for studies that use convolutional networks to explain activity in the visual system. Here we study plausible alternatives to weight sharing that aim at the same regularization principle, which is to make each neuron within a pool react similarly to identical inputs. The most natural way to do that is by showing the network multiple translations of the same image, akin to saccades in animal vision. However, this approach requires many translations, and doesn't remove the performance gap. We propose instead to add lateral connectivity to a locally connected network, and allow learning via Hebbian plasticity. This requires the network to pause occasionally for a sleep-like phase of "weight sharing". This method enables locally connected networks to achieve nearly convolutional performance on ImageNet, thus supporting convolutional networks as a model of the visual stream.


page 1

page 2

page 3

page 4


Learning in the Machine: To Share or Not to Share?

Weight-sharing is one of the pillars behind Convolutional Neural Network...

BioLCNet: Reward-modulated Locally Connected Spiking Neural Networks

Recent studies have shown that convolutional neural networks (CNNs) are ...

Automatic Neuron Detection in Calcium Imaging Data Using Convolutional Networks

Calcium imaging is an important technique for monitoring the activity of...

Multi-Scale Weight Sharing Network for Image Recognition

In this paper, we explore the idea of weight sharing over multiple scale...

Theoretical Analysis of Inductive Biases in Deep Convolutional Networks

In this paper, we study the inductive biases in convolutional neural net...

BEAN: Interpretable Representation Learning with Biologically-Enhanced Artificial Neuronal Assembly Regularization

Deep neural networks (DNNs) are known for extracting good representation...

Convolutional Networks in Visual Environments

The puzzle of computer vision might find new challenging solutions when ...

Please sign up or login with your details

Forgot password? Click here to reset