Bayesian Deep learning with 10% of the weights - Rob Romijnders
PyData Amsterdam 2018
Deep learning grows in popularity and use, but it has two problems. Neural networks have millions of parameters and provide no uncertainty. In this talk, we solve both problems with one simple trick: Bayesian deep learning. We show how to prune 90% of the parameters while maintaining performance. As a bonus, we get the uncertainty over our predictions, which is useful for critical applications.
Slides: https://github.com/RobRomijnders/weight_uncertainty/blob/master/docs/presentation/versions/final_pydata18_bayes_nn_rob_romijnders_1.pdf
--
www.pydata.org
PyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R.
PyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!
00:10 Help us add time stamps or captions to this video! See the description for details.
Want to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps
Видео Bayesian Deep learning with 10% of the weights - Rob Romijnders канала PyData
Deep learning grows in popularity and use, but it has two problems. Neural networks have millions of parameters and provide no uncertainty. In this talk, we solve both problems with one simple trick: Bayesian deep learning. We show how to prune 90% of the parameters while maintaining performance. As a bonus, we get the uncertainty over our predictions, which is useful for critical applications.
Slides: https://github.com/RobRomijnders/weight_uncertainty/blob/master/docs/presentation/versions/final_pydata18_bayes_nn_rob_romijnders_1.pdf
--
www.pydata.org
PyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R.
PyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases. 00:00 Welcome!
00:10 Help us add time stamps or captions to this video! See the description for details.
Want to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps
Видео Bayesian Deep learning with 10% of the weights - Rob Romijnders канала PyData
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
Eric J. Ma - An Attempt At Demystifying Bayesian Deep LearningVincent Warmerdam: How to Constrain Artificial Stupidity | PyData London 2019I built my own AlphaZero to master the game of 2048Andrew Rowan - Bayesian Deep Learning with Edward (and a trick using Dropout)Vincent Warmerdam: Gaussian Progress | PyData Berlin 2019History of Bayesian Neural Networks (Keynote talk)Probabilistic Programming and Bayesian Modeling with PyMC3 - Christopher FonnesbeckThe Kernel Trick - THE MATH YOU SHOULD KNOW!Uncertainty in Neural Networks? Monte Carlo DropoutVincent Warmerdam: Winning with Simple, even Linear, Models | PyData London 2018Pruning Deep Learning Models for Success in ProductionForecasting revenues in Business CasesBayesian Neural Network | Deep LearningIntroduction to Bayesian statistics, part 1: The basic conceptsJ. Frankle & M. Carbin: The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural NetworksIgor Gotlibovych: Deep Learning and Time Series Forecasting for Smarter Energy | PyData London 2019Bayesian-Neural Network Ensemble Modeling: Results from an Initial ExperimentUncertainty estimation and Bayesian Neural Networks - Marcin MożejkoMagnitude-based weight pruning with Tensorflow