Building smarter solutions without machine learning expertise
summary
Shows how to build practical ML systems without specialist knowledge by using pre-trained vision APIs, cloud NLP and speech services (OCR, face/emotion detection, translation, WaveNet TTS) and AutoML. Demonstrates AutoML image training on ~100–1,000 images to reach about 90% accuracy with short runs (15–20 minutes) and longer tuning (1–3 hours), exporting models to run in-browser at ~4–5 predictions/sec, and contrasts quick API integrations (hours) with building custom models (days–weeks); also covers AutoML Tables for structured data.
AI-written summary · about
chapters (12)
- 0:00Introduction to AI for non-experts
- 1:05Machine learning definition and stakes
- 3:12Using ML in business
- 4:55Ready-to-use ML APIs
- 14:55Vision API demo
- 17:21Text processing with NLP
- 21:53Automatic translation and speech-to-text
- 26:22Speech-to-text and synthetic voice
- 32:22AutoML for custom models
- 39:03AutoML vision demo
- 43:18AutoML technologies and frameworks
- 45:49Summary and outlook
related talks
01h 08mAutoML: 40 hours of doing machine learning without knowing it
57mBuilding smarter solutions with Machine Learning, from magic to reality
54mBuilding smarter apps with Machine Learning, from magic to reality
48mBuilding Smarter Solutions Without Machine Learning Expertise
47mBuilding smarter apps with Machine Learning, from magic to reality
44mBuilding smarter solutions with no expertise in machine learning
56mBuilding Intelligent Apps with Machine Learning
22mTrain Custom Machine Learning Models with No Data Science Expertise