In this talk, we want to walk through two machine learning scopes as supervised and unsupervised learning. Most part of this talk will be focused on the second one, and when the minds are boiled, we will try to move around adversarial training with Generative Adversarial Networks. After that, we will be focused on different research ideas for using this network structure in different applications and I hope we will cover some ideas in implementing, stabilizing and different important factors to train adversarial networks.
Mohammad Khalooei is a Ph.D candidate at Amirkabir University of Technology (Tehran Polytechnic) in the department of computer engineering. He works at the Laboratory of Intelligence and Multimedia Processing of AUT. He is interested in artificial intelligence fields and working on vulnerability of deep neural network, adversarial machine learning and unsupervised learning in theoretical and also deployment phases. He also has some experiences in counseling on using deep neural networks for real data processing and joint international project.