- Data preparation
- Feature selection and resampling
- Decision Tree and Random Forest
- Logistic Regression and Nearest Neighbors
- TensorFlow and Keras
- Image processing
- RNN and sequential data
- Real life applications
- 1.5 hours of in-person lecture + 1.5 hours of lab per week
- Scoring: written exam 70% + group project 30%
- Understanding LSTM
- The Unreasonable Effectiveness of Recurrent Neural Networks
- Neural Networks & The Backpropagation Algorithm
- Things to note: tanh, sigmoid, relu functions