Machine Learning for developers in a hurry
summary
Shows how to build working ML quickly using Google Cloud Translation, Speech-to-Text and Text-to-Speech APIs to transcribe, translate and dub YouTube videos as a rapid prototype, and uses Video Intelligence API to get bounding boxes from a GoPro clip in about 15 minutes. Demonstrates training a custom fraud model from BigQuery with Vertex AI AutoML, running for one node hour, reports a confusion matrix and deploys batch jobs or a REST endpoint. Emphasizes TensorFlow Hub and TensorFlow.js for browser inference and reusable components AutoML.
AI-written summary · about
chapters (10)
- 0:00Start
- 0:36What is Machine Learning?
- 0:47Machine Learning unlocks
- 1:09Timing software projects is hard.
- 1:27Learning Collecting curve data
- 2:07The key? Choosing the right problems
- 2:21Good tools
- 3:22What makes these problems easy?
- 3:38Translation Speech-to-Text
- 11:391. Choose the right problems
related talks
54mBuilding smarter apps with Machine Learning, from magic to reality
44mBuilding smarter solutions with no expertise in machine learning
57mBuilding smarter solutions with Machine Learning, from magic to reality
47mBuilding smarter apps with Machine Learning, from magic to reality
47mBuilding smarter solutions without machine learning expertise
42mUse Machine Learning in your code, without being a ML expert
32mMachine Learning for Game Developers
17mAI/ML demo derby