Interview with Martin Görner

on YouTube ↗09m

" summary

TensorFlow is presented as a researcher-grade Python library designed to be production-ready, now with TensorFlow 1.4 and higher-level APIs that make model building practical for regular developers. Google Cloud ML Engine hyperparameter tuning runs multiple trials with Bayesian optimization so large jobs can scale and find good parameters automatically. The library offers a sequence-to-sequence with attention API that rebuilt Google Translate in ten lines, plus a layers/Estimator API that simplifies convnets, RNNs and deployment.

AI-written summary · about

" chapters (6)

1. 0:00Introduction
2. 0:46What is Tensorflow
3. 2:10Learning a new language
4. 3:17Learning Python
5. 4:30Learning Tensorflow
6. 5:23ML Engine

" related talks

• 01mWe Talk withGema Parreño · Codemotion Madrid 2016
• 07mMachine learning at GoogleRob Craft · Strata + Hadoop World 2017
• 13mTaking Machine Learning to the Next LevelGiovanni Galloro · Codemotion Rome 2018
• 41mTensorFlow ever higherYoann Benoit · DevFest Paris 2019
• 59mMachine Intelligence at Google ScaleGuillaume Laforge · Voxxed Days Singapore 2017
• 38mCutting Edge TensorFlow: New TechniquesElie Burzstein, Josh Dillon, Michael Bendersky, Sofien Bouaziz · Google I/O 2019
• 05mInterviewChris Fregly · AI By the Bay 2017
• 28mTensorFlow 1.0: open source machine learningAndrew Selle · FOSSASIA Summit 2017