Topological deep learning algorithm with visual impression
Mengduo Yang, Fanzhang Li · 2017
We present in this paper a novel approach for training a topological deep neural network with visual impression. We show that by combing denoising auto-encoder model and contractive auto-encoder with Hessian regularization model, we can achieve a deterministic auto-encoder aiming for robustness to small variations of the input. We exploit the tangent propagation algorithm to show how our algorithm can capture the manifold structure of the visual impression and build a topological atlas of charts. Finally, we show that by using the learned features to initialize a deep network, we achieve superior classification with relatively smaller parameters than some other models.