Transfer Learning on an Autoencoder-based Deep Network. Leandro Fabio Ariza Jiménez PhD student in Mathematical Engineering, GRIMMAT – Research group in mathematical modeling, EAFIT University. Agosto 22 de 2016. PhD in Mathematical Engineering. Seminar of the PhD in Mathematical Engineering.
Abstract: It is widely known that deep neural networks can be dicult to train in practice, since in order to obtain state-of-the-art results we need a great amount of data and computing power. However, we can overcome this issue either using autoencoders as way to “pre-train” deep neural networks or following a “transfer learning” approach. In particular, here we carried out several experiments to study how both approaches can bene?t the training of deep networks.