Improving Self-Organizing Maps with Unsupervised Feature Extraction

TL;DR

This paper enhances Self-Organizing Maps by integrating unsupervised feature extraction methods, leading to improved classification accuracy and state-of-the-art performance in unsupervised image classification tasks.

Contribution

It introduces the use of feature extraction via auto-encoders and spiking neural networks to improve SOM performance on complex datasets.

Findings

SOM classification accuracy improved by +6.09%.

Achieved state-of-the-art results in unsupervised image classification.

Demonstrated the impact of feature maps, SOM size, and labeled data on accuracy.

Abstract

The Self-Organizing Map (SOM) is a brain-inspired neural model that is very promising for unsupervised learning, especially in embedded applications. However, it is unable to learn efficient prototypes when dealing with complex datasets. We propose in this work to improve the SOM performance by using extracted features instead of raw data. We conduct a comparative study on the SOM classification accuracy with unsupervised feature extraction using two different approaches: a machine learning approach with Sparse Convolutional Auto-Encoders using gradient-based learning, and a neuroscience approach with Spiking Neural Networks using Spike Timing Dependant Plasticity learning. The SOM is trained on the extracted features, then very few labeled samples are used to label the neurons with their corresponding class. We investigate the impact of the feature maps, the SOM size and the labeled subset size on the classification accuracy using the different feature extraction methods. We improve the SOM classification by +6.09\% and reach state-of-the-art performance on unsupervised image classification.