Building smarter apps with Machine Learning, from magic to reality
summary
Demo shows concrete tools and outcomes: Vision, Natural Language, Video Intelligence, Speech‑to‑Text and WaveNet text‑to‑speech plus Translate are used via Google Cloud APIs; a Cloud Storage pipeline triggers Vision analysis, composes images and crops the largest face in real time. AutoML trains custom models from about 2,000 samples, improving from ~85% precision after one hour to ~92% after longer training; one user reaches 97% species ID accuracy. Examples include OCR, entity linking across image+text, sentiment scoring, and real‑time speech transcription.
AI-written summary · about
chapters (10)
- 0:00Introduction and background
- 2:02What is machine learning
- 5:38Machine learning APIs as building blocks
- 15:49Live demo with Vision API
- 20:14Video and text APIs overview
- 26:14Live demo with translation and NLP
- 30:58Speech-to-text and text-to-speech
- 34:14Custom models with AutoML
- 42:46Wrap-up and next steps
- 43:49Q&A session
related talks
57mBuilding smarter solutions 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
59mMachine Intelligence at Google Scale
42mMachine Learning APIs, from Training [...]
42mUse Machine Learning in your code, without being a ML expert
36mCloud AI Services: What they are and how to use them
47mBuilding smarter solutions without machine learning expertise