Unsupervised Features Extracted using Winner-Take-All Mechanism Lead to Robust Image Classification

Leading mainstream image processing approaches produce excellent performance using convolutional neural networks trained by backpropagation (BP) learning rules. Unsupervised learning approaches have been popular due to their biological significance, though they typically underperform compared to BP results. In this work, we demonstrate that features extracted in an unsupervised manner using the biologically inspired Hebbian learning rule in a winner-take-all setting, perform competitively with BP on the image classification task. The convolutional filters learned by Hebbian rule are smoother than filters learned using BP. The quality of the two training approaches is compared based on metrics such as the speed of training and classification accuracy. We demonstrate that the extracted features of unsupervised learning are more robust to noise as compared to BP.