Self-organizing neurons: toward brain-inspired unsupervised learning
Résumé
During the last years, Deep Neural Networks have reached the highest performances in image classification Nevertheless,such a success is mostly based on supervised and off-line learning: they require thus huge labeled datasets for learning,and once it is done, they cannot adapt to any change in the data from the environment. In the context of brain-inspired computing, we apply Kohonen-based Self-Organizing Maps for unsupervised learning without labels, and we explore original extensions such as the Dynamic SOM that enables continuous learning and the Pruning Cellular SOM that includes synaptic pruning in neuromorphic circuits. After presenting the three models and the experimental setup for MNIST classification, we compare different methods for automatic labeling based on
very few labeled data (1% of the training dataset), and then we compare the performances of the three Kohonen-based Self-Organizing Maps with STDP-based Spiking Neural Networks in terms of accuracy, dynamicity and scalability.
Mots clés
self-organizing neurons
Kohonen-based self-organizing maps
embedded image classification
pruning cellular SOM
STDP-based spiking neural networks
dynamic SOM
image classification
unsupervised learning
self-organizing maps
brain-inspired computing
deep neural networks
neuromorphic circuits
automatic labeling
MNIST classification
synaptic pruning
continuous learning