Bayesian Hyperparameter Optimization for PyTorch (8.4)

Unlock the power of Bayesian optimization for refining your PyTorch models in this enlightening tutorial. Traditional methods for hyperparameter tuning, while effective, can often be time-consuming and computationally expensive. Enter Bayesian Hyperparameter Optimization - a probabilistic approach that aims to determine the best hyperparameters more efficiently, ensuring your models perform at their peak. In this video, we walk through the foundations of Bayesian reasoning in the context of PyTorch, guiding you step-by-step on how to integrate this technique into your deep learning workflow.
Code for This Video:
github.com/jeffheaton/app_dee...
~~~~~~~~~~~~~~~ COURSE MATERIAL ~~~~~~~~~~~~~~~
📖 Textbook - Coming soon
😸🐙 GitHub - github.com/jeffheaton/app_dee...
▶️ Play List - • 2023 PyTorch Version A...
🏫 WUSTL Course Site - sites.wustl.edu/jeffheaton/t8...
~~~~~~~~~~~~~~~ CONNECT ~~~~~~~~~~~~~~~
🖥️ Website: www.heatonresearch.com/
🐦 Twitter - / jeffheaton
😸🐙 GitHub - github.com/jeffheaton
📸 Instagram - / jeffheatondotcom
🦾 Discord: / discord
▶️ Subscribe: ua-cam.com/users/heatonresea...
~~~~~~~~~~~~~~ SUPPORT ME 🙏~~~~~~~~~~~~~~
🅿 Patreon - / jeffheaton
🙏 Other Ways to Support (some free) - www.heatonresearch.com/suppor...
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#BayesianOptimization #PyTorch #HyperparameterTuning #DeepLearning #ProbabilisticApproach #ModelOptimization #BayesianHyperparameters #PyTorchTuning #AdvancedML #EfficientTraining

[@fernandoferreiradelima9040]

It was really useful for me. Thank you for this videos.

[@warssup]

It's nice to see that you use it almost identically as I do. One the one side that's natural if everyone is doing it correctly but also its nice to have this little confidence boost as others to it the same way and that means I do it correctly.
Anyhow, have you thoughts on AutoML packages like autoPyTorch as they do this complete stuff already under the hood and even more. For me, I was never truely that succesfull just using an AutoML tool and "brute-force" things from the beginning.