Towards Automated Deep Learning
We are happy to announce a new series of meetups in the field of artificial intelligence (AI) in Freiburg. Please feel warmly invited to our first tech talk which will take place on October 24th starting at 19:00 in the “Baumraum” at Grünhof Freiburg. We are excited that the leader of the Machine Learning Lab at University Freiburg, Prof. Frank Hutter, followed our invitation and will give a talk about Towards Automated Deep Learning.
After the talk, there is time for an open discussion. This event is free and open for everyone who is interested in the broad field of AI.
Abstract of the talk:
The performance of most deep learning methods heavily depends on the chosen network architectures and their hyperparameters. In this talk, I will discuss methods for effective optimization in this combined space, thereby paving the way to fully automated end-to-end deep learning. Next to competition-winning AutoML systems, I will discuss BOHB, a robust and efficient multi-fidelity hyperparameter optimization system that is parallelizable and applicable to tuning a wide range of deep learning methods, as well as recent advances in neural architecture search. I will end with an application of AutoML to the problem of learning to design RNA using deep reinforcement learning (RL), in which we used BOHB to jointly tune the RL agent's state representation, its policy network's architecture, and its hyperparameters, yielding a clear new state-of-the-art in RNA design.
For more information -> https://www.automl.org