Biologically plausible deep learning -- but how far can we go with shallow networks?

TL;DR

This paper explores the capabilities of shallow, biologically plausible neural networks with local learning rules on MNIST and CIFAR10, achieving near state-of-the-art accuracy and challenging the necessity of deep architectures.

Contribution

It demonstrates that shallow networks with local learning rules and simple architectures can reach high accuracy, questioning the need for deep networks in biologically plausible models.

Findings

Shallow networks with local learning rules can reach over 98% accuracy on MNIST.

Localized receptive fields outperform all-to-all connectivity in these models.

Spiking neuron implementations achieve comparable performance to rate-based models.

Abstract

Training deep neural networks with the error backpropagation algorithm is considered implausible from a biological perspective. Numerous recent publications suggest elaborate models for biologically plausible variants of deep learning, typically defining success as reaching around 98% test accuracy on the MNIST data set. Here, we investigate how far we can go on digit (MNIST) and object (CIFAR10) classification with biologically plausible, local learning rules in a network with one hidden layer and a single readout layer. The hidden layer weights are either fixed (random or random Gabor filters) or trained with unsupervised methods (PCA, ICA or Sparse Coding) that can be implemented by local learning rules. The readout layer is trained with a supervised, local learning rule. We first implement these models with rate neurons. This comparison reveals, first, that unsupervised learning does not lead to better performance than fixed random projections or Gabor filters for large hidden layers. Second, networks with localized receptive fields perform significantly better than networks with all-to-all connectivity and can reach backpropagation performance on MNIST. We then implement two of the networks - fixed, localized, random & random Gabor filters in the hidden layer - with spiking leaky integrate-and-fire neurons and spike timing dependent plasticity to train the readout layer. These spiking models achieve > 98.2% test accuracy on MNIST, which is close to the performance of rate networks with one hidden layer trained with backpropagation. The performance of our shallow network models is comparable to most current biologically plausible models of deep learning. Furthermore, our results with a shallow spiking network provide an important reference and suggest the use of datasets other than MNIST for testing the performance of future models of biologically plausible deep learning.