Building smarter solutions with Machine Learning, from magic to reality
summary
Shows concrete Google Cloud tools and live results: Vision, Video Intelligence, Natural Language, Speech-to-Text and WaveNet TTS, plus AutoML Vision that trains a custom model from labeled images. Demo pipeline uses 383 Python functions and serverless buckets to add moustaches and detect emotions from selfies. AutoML example trains in about one hour (distributed ~15 min), then three compute-hours to reach 92% accuracy; a conservation user processes half a million images in days instead of a year.
AI-written summary · about
chapters (15)
- 0:00Start
- 4:52The Usage of Machine Learning at Google
- 6:27Ready To Use Machine Learning Models
- 8:00Examples with Google Cloud Machine Learning Solutions
- 8:31Favorite Api
- 19:48Live Demo
- 22:05Machine Learning Api
- 25:14Video Intelligence Api
- 26:50Natural Language
- 32:18Sample Sentences in Different Languages
- 34:27Convert Speech to Text
- 36:22Text-to-Speech Engines
- 40:48The Confusion Matrix
- 44:19Transfer Learning
- 44:46Machine Learning for Machine Learning
related talks
47mBuilding smarter apps with Machine Learning, from magic to reality
54mBuilding smarter apps with Machine Learning, from magic to reality
44mBuilding smarter solutions with no expertise in machine learning
42mUse Machine Learning in your code, without being a ML expert
59mMachine Intelligence at Google Scale
42mMachine Learning APIs, from Training [...]
47mBuilding smarter solutions without machine learning expertise
22mTrain Custom Machine Learning Models with No Data Science Expertise