PyData Calgary

For this session we will be running a hands-on workshop. Expect a brief introduction to the problem, followed by hacking time. Come prepared to code! For this session we will focus on hyperparameter tuning. - Skill level: Intermediate - Prerequisites: Basic proficiency in model development and evaluation - What to bring: Laptop and ample power. CPU only is fine - Libraries to install: scikit-learn, scikit-optimize, hyperopt, bayesian-optimization What we'll work on: - Implement grid + random search optimization - Optimize model using at least one Bayesian method - Compare & contrast tree of parzen estimators, Gaussian processes, regression trees - Experiment with popular libraries Space is limited in the venue, so please be mindful of your RSVPs. A good briefing can be found here https://towardsdatascience.com/a-conceptual-explanation-of-bayesian-model-based-hyperparameter-optimization-for-machine-learning-b8172278050f