Summary

1. AI first
2. Create good ML datasets, then building your first ML model with TensorFlow
3. Improving ML accuracy
4. ML at scale
5. Specialized ML models
   • Image classification models
   • Sequence models
   • Recommendation systems

Two stages of ML

1. Train an ML model with examples (Training)
   • label - true answer
   • model - mathematical function
2. Predict with a trained model (Inference)

Adjust function so that outputs of model for set of training inputs is as close as possible to the training labels