Online Representation Learning with Multi-layer Hebbian Networks for Image Classification Tasks

Unsupervised learning allows algorithms to adapt to different data thanks to the autonomous discovery of discriminating features during the training. When these algorithms are reducible to cost-function minimisation, better interpretations of their learning dynamics are possible. Recently, new Hebbian-like plasticity, bio-inspired, local and unsupervised learning rules for neural networks, have been shown to minimise a cost-function while performing online sparse representation learning. However, it is unclear to what degree such rules are effective to learn features from images. To investigate this point, this study introduces a novel multi-layer Hebbian network trained by a rule derived from a non-negative classical multidimensional scaling cost-function. The performance is compared to that of other fully unsupervised learning algorithms.