Workshop on Deep Neural Learning and Bayesian Optimization of Hyperparameters


Date
Apr 23, 2020 8:00 PM
Location
Hamburg, Germany

The (online) workshop is organized by Hamburger Informatik Technologie-Center e.V. (HITeC) and Artificial Intelligence Center Hamburg e.V. (ARIC) on 9th, 16th, and 23rd April 2020. The focus of the workshop was on optimizing hyperparameters of deep learning models with Bayesian optimization. In this workshop, participants learned how to write searchable deep learning models in Pytorch and searching for hyperparameters with one of the latest AutoML methods. Bayesian Optimization and HyperBand ( BOHB) is introduced for hyperparameter optimization. On each day, there was a practical session for implementing the concepts on Google Colaboratory.

The content of the workshop was:

  • Day 1 (09.04.2020) Introduction to Neural Network
    • Basics of Neural Network
    • Basics of Pytorch
    • Multi-Layer Perceptron
    • Hands-on Session
  • Day 2 (16.04.2020) Convolutional Neural Network
    • Questions from the previous session
    • Basics of Convolutional Neural Network
    • Convolutional Neural Network in Pytorch
    • Hands-on Session
  • Day 3 (23.04.2020) Bayesian Optimization
    • Questions from the previous session
    • Introduction of Bayesian Optimization
    • Introduction of BOHB Framework
    • Writing a Searchable Architecture
    • Hands-on Session
Mohammad Ali Zamani
Mohammad Ali Zamani
Machine Learning Applied Scientist

I am Machine Learning Applied Scientist at Hamburg Informatics Technology Center (HITeC) and a Research Associate at University of Hamburg. My research interests include Deep Reinforcement Learning, Computer Vision, Cognitive Robotics and Natural Language Processing.