Hebbian Semi-Supervised Learning in a Sample Efficiency Setting

Abstract

We propose to address the issue of sample efficiency, in Deep Convolutional Neural Networks (DCNN), with a semi-supervised training strategy that combines Hebbian learning with gradient descent: all internal layers (both convolutional and fully connected) are pre-trained using an unsupervised approach based on Hebbian learning, and the last fully connected layer (the classification layer) is trained using Stochastic Gradient Descent (SGD). In fact, as Hebbian learning is an unsupervised learning method, its potential lies in the possibility of training the internal layers of a DCNN without labels. Only the final fully connected layer has to be trained with labeled examples. We performed experiments on various object recognition datasets, in different regimes of sample efficiency, comparing our semi-supervised (Hebbian for internal layers + SGD for the final fully connected layer) approach with end-to-end supervised backprop training, and with semi-supervised learning based on Variational Auto-Encoder (VAE). The results show that, in regimes where the number of available labeled samples is low, our semi-supervised approach outperforms the other approaches in almost all the cases.

arXiv comment18 pages, 9 figures, 3 tables, accepted by Elsevier Neural Networks

References in corpus (12)

• Auto-Encoding Variational Bayes
• A Simple Framework for Contrastive Learning of Visual Representations
• How transferable are features in deep neural networks?
• Semi-Supervised Learning with Deep Generative Models
• Semi-Supervised Learning with Ladder Networks
• A CMOS Spiking Neuron for Brain-Inspired Neural Networks with Resistive Synapses and In-Situ Learning
• Unsupervised Learning by Competing Hidden Units
• Augmenting Supervised Neural Networks with Unsupervised Objectives for Large-scale Image Classification
• A Hebbian/Anti-Hebbian Neural Network for Linear Subspace Learning: A Derivation from Multidimensional Scaling of Streaming Data
• Analyzing the Performance of Multilayer Neural Networks for Object Recognition
• Optimization theory of Hebbian/anti-Hebbian networks for PCA and whitening
• Learning Sparse, Distributed Representations using the Hebbian Principle

Cited by in corpus (3)

• SoftHebb: Bayesian Inference in Unsupervised Hebbian Soft Winner-Take-All Networks
• Self-Contrastive Forward-Forward Algorithm
• Unsupervised Hebbian Learning on Point Sets in StarCraft II