Building smarter solutions with no expertise in machine learning

on YouTube ↗44m

" summary

Claim: developers get working ML features in hours and custom models in days using Google Cloud tools. Uses Vision API, Video Intelligence, NLP, Speech-to-Text, WaveNet text-to-speech and AutoML on Vertex AI. Example: cloud classifier trained from ~300 labeled photos reaches 90% precision after a few iterative runs; exported to TensorFlow.js and runs in-browser detecting chips on a board at 4–5 predictions/sec; WaveNet generates speech ~20× real time.

AI-written summary · about

" chapters (17)

1. 0:00Start
2. 2:16What is machine learning?
3. 2:35What is machine learning, for real?
4. 3:03How does deep learning work?
5. 6:44Label detection
6. 7:29Object detection
7. 7:47Face detection
8. 8:24Text detection
9. 10:10Handwriting detection
10. 11:25Web entity detection and image matching
11. 17:42Syntax analysis
12. 19:33Content classification
13. 20:14Sentiment analysis
14. 25:34Speech timestamps
15. 26:51Text-to-Speech API
16. 37:58Transfer learning
17. 38:20Hyperparameter tuning

" related talks

• 57mBuilding smarter solutions with Machine Learning, from magic to realityLaurent Picard · code.talks commerce 2019
• 54mBuilding smarter apps with Machine Learning, from magic to realityLaurent Picard · Voxxed Days Cluj-Napoca 2018
• 47mBuilding smarter apps with Machine Learning, from magic to realityLaurent Picard · GDG DevFest Poland 2018 in Wrocław
• 42mUse Machine Learning in your code, without being a ML expertAlfredo Morresi · Codemotion Rome 2018
• 59mMachine Intelligence at Google ScaleGuillaume Laforge · Voxxed Days Singapore 2017
• 14mMachine Learning for developers in a hurryDale Markowitz · Google I/O 2022
• 47mBuilding smarter solutions without machine learning expertiseLaurent Picard · Devoxx France 2021
• 36mCloud AI Services: What they are and how to use themKarl Weinmeister · Global Artificial Intelligence Conference 2020