Building smarter apps with Machine Learning, from magic to reality
summary
Shows how to build working features with Google Cloud ML: uses Vision API for face, landmark and label detection, Video Intelligence for shot-level labels, Natural Language and Translate for entity and sentiment extraction, Speech-to-Text/Text-to-Speech with WaveNet, and AutoML Vision for custom classifiers. Demonstrates a serverless pipeline (Cloud Storage → Cloud Functions → JSON results) deployed in ~20 minutes, trains AutoML models (1–3 hour runs), and cites real wins: Airbnb 60% cross‑language users and camera projects cutting 6 months of labeling to days.
AI-written summary · about
chapters (6)
- 0:00Start
- 2:54How does ML work?
- 8:47Landmark detection
- 11:06Label & text detection
- 39:02Text-to-Speech API
- 51:34Model precision
related talks
57mBuilding smarter solutions with Machine Learning, from magic to reality
47mBuilding smarter apps with Machine Learning, from magic to reality
44mBuilding smarter solutions with no expertise in machine learning
59mMachine Intelligence at Google Scale
42mUse Machine Learning in your code, without being a ML expert
47mBuilding smarter solutions without machine learning expertise
42mMachine Learning APIs, from Training [...]
14mMachine Learning for developers in a hurry