DeepAI AI Chat
Log In Sign Up

Improving Self-Organizing Maps with Unsupervised Feature Extraction

by   Lyes Khacef, et al.

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.


page 1

page 2

page 3

page 4


Locally Connected Spiking Neural Networks for Unsupervised Feature Learning

In recent years, Spiking Neural Networks (SNNs) have demonstrated great ...

Unsupervised Learning with Self-Organizing Spiking Neural Networks

We present a system comprising a hybridization of self-organized map (SO...

Topological Gradient-based Competitive Learning

Topological learning is a wide research area aiming at uncovering the mu...

Unsupervised Parallel Extraction based Texture for Efficient Image Representation

SOM is a type of unsupervised learning where the goal is to discover som...

Gradient Driven Learning for Pooling in Visual Pipeline Feature Extraction Models

Hyper-parameter selection remains a daunting task when building a patter...

Attentional Neural Network: Feature Selection Using Cognitive Feedback

Attentional Neural Network is a new framework that integrates top-down c...

Relevant feature extraction for statistical inference

We introduce an algorithm that learns correlations between two datasets,...