Gilles Louppe | Bayesian optimization with Scikit-Optimize
PyData Amsterdam 2017
You are given access to an espresso machine with many buttons and knobs to tweak. Your task is to brew the best cup of espresso possible. How do you find the best settings before dying of a caffeine overdose? The answer is bayesian optimisation: the art of minimising an extremely expensive to evaluate function in as few calls as possible.
Bayesian optimisation can be applied to finding the optimal hyper-parameters for a deep neural network, optimizing the click-through-rate in online advertising or simulator settings of an optimal physics experiment. This talk will teach you about the basics of bayesian optimisation and how to use Scikit-Optimize to apply it to your own real world problems.
In addition to learning how to use this toolkit, you will also learn the answers to questions like:
When is bayesian optimisation useful? What is bayesian about bayesian optimisation? When can a statistical model be used for bayesian optimisation? What is an acquisition function and how does it help to exploit / explore the search space?
We will end the talk with an example to optimize hyperparameters of a neural-network using bayesian optimisation.
Видео Gilles Louppe | Bayesian optimization with Scikit-Optimize канала PyData
You are given access to an espresso machine with many buttons and knobs to tweak. Your task is to brew the best cup of espresso possible. How do you find the best settings before dying of a caffeine overdose? The answer is bayesian optimisation: the art of minimising an extremely expensive to evaluate function in as few calls as possible.
Bayesian optimisation can be applied to finding the optimal hyper-parameters for a deep neural network, optimizing the click-through-rate in online advertising or simulator settings of an optimal physics experiment. This talk will teach you about the basics of bayesian optimisation and how to use Scikit-Optimize to apply it to your own real world problems.
In addition to learning how to use this toolkit, you will also learn the answers to questions like:
When is bayesian optimisation useful? What is bayesian about bayesian optimisation? When can a statistical model be used for bayesian optimisation? What is an acquisition function and how does it help to exploit / explore the search space?
We will end the talk with an example to optimize hyperparameters of a neural-network using bayesian optimisation.
Видео Gilles Louppe | Bayesian optimization with Scikit-Optimize канала PyData
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
![Thomas Huijskens - Bayesian optimisation with scikit-learn](https://i.ytimg.com/vi/jtRPxRnOXnk/default.jpg)
![Machine learning - Bayesian optimization and multi-armed bandits](https://i.ytimg.com/vi/vz3D36VXefI/default.jpg)
![Optuna: A Define-by-Run Hyperparameter Optimization Framework | SciPy Japan | Shotaro Sano, et al](https://i.ytimg.com/vi/tcrcLRopTX0/default.jpg)
![Bayes theorem](https://i.ytimg.com/vi/HZGCoVF3YvM/default.jpg)
![Google's self-learning AI AlphaZero masters chess in 4 hours](https://i.ytimg.com/vi/0g9SlVdv1PY/default.jpg)
![Basics of Bayesian Optimization (Supplementary Video for SIGGRAPH 2017)](https://i.ytimg.com/vi/WkZueBgKFYM/default.jpg)
![Vincent Warmerdam: Winning with Simple, even Linear, Models | PyData London 2018](https://i.ytimg.com/vi/68ABAU_V8qI/default.jpg)
![Prof. Brian Cox - Machine Learning & Artificial Intelligence - Royal Society](https://i.ytimg.com/vi/YvEIEXE_NL0/default.jpg)
![How to find the best model parameters in scikit-learn](https://i.ytimg.com/vi/Gol_qOgRqfA/default.jpg)
![Nicole Carlson - Turning PyMC3 into scikit learn](https://i.ytimg.com/vi/zGRnirbHWJ8/default.jpg)
![Bayesian A/B Testing - Marc Garcia](https://i.ytimg.com/vi/UxEFAkDlkiA/default.jpg)
![A visual guide to Bayesian thinking](https://i.ytimg.com/vi/BrK7X_XlGB8/default.jpg)
![Kevin Goetsch | Deploying Machine Learning using sklearn pipelines](https://i.ytimg.com/vi/URdnFlZnlaE/default.jpg)
![Optuna: A Define by Run Hyperparameter Optimization Framework | SciPy 2019 |](https://i.ytimg.com/vi/J_aymk4YXhg/default.jpg)
![Building a black box optimizer in Python with scikit-optimize](https://i.ytimg.com/vi/pALURSgI2sY/default.jpg)
![Frequentist, Likelihood, and Bayesian Approaches to Statistical Inferences by Daniel Lakens](https://i.ytimg.com/vi/7-Ud4nyHO_Q/default.jpg)
![TPE: how hyperopt works](https://i.ytimg.com/vi/tdwgR1AqQ8Y/default.jpg)
![Google's Deep Mind Explained! - Self Learning A.I.](https://i.ytimg.com/vi/TnUYcTuZJpM/default.jpg)
![2. Bayesian Optimization](https://i.ytimg.com/vi/C5nqEHpdyoE/default.jpg)
!["Bayesian Optimization for Machine Learning and Science" (CRCS Lunch Seminar)](https://i.ytimg.com/vi/a79klpzaPgY/default.jpg)