Self-organizing neurons: toward brain-inspired unsupervised learning

Lyes Khacef (1) , Benoit Miramond (1) , Diego Barrientos (2) , Andres Upegui (2)

1 LEAT - Laboratoire d'Electronique, Antennes et Télécommunications
2 INIT - Institute of New Imaging Technologies

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

Domaines: Réseau de neurones [cs.NE]; Architectures Matérielles [cs.AR]; Bio-informatique [q-bio.QM]

Lyes Khacef, Benoit Miramond, Diego Barrientos, Andres Upegui. Self-organizing neurons: toward brain-inspired unsupervised learning. The International joint Conference On Neural Networks, Jul 2019, Budapest, Hungary. pp.1-9, ⟨10.1109/IJCNN.2019.8852098⟩. ⟨hal-02078129⟩