Gradient Based Optimization Methods

Our newest PhD student, Andrinandrasana David Rasamoelina presented his research in a seminar titled “Recent Advances in Gradient Based Optimization Method for Deep Neural Network”.

He gave an introduction to gradient-based optimization for deep neural networks, the history and problem caused by selected optimization algorithms which led to the elaboration of the recent state-of-the-art methods. He also provided a quick overview on the convergence of Deep Neural Network and which optimization algorithm to use for a specific problem.

optimizers_1
optimizers_3
optimizers_2