Lectures subject to change, up until the day of the lecture.

1. T 8/27: Overview; Spectrograms. HTML, Jupyter source.
2. R 8/29: Fourier Transforms: MOV, WMV, MP4, Sample Problems, Solutions.
3. T 9/3: Filtering. MOV, WMV, MP4, Sample Problems, Solutions.
4. R 9/5: Zero-Mean White Gaussian Noise. MOV, WMV, MP4, Sample Problems, Solutions.
5. T 9/10: Principal Component Analysis. Slides: PPTX, PDF. Sample Problems, Solutions.
6. R 9/12: Discrete Cosine Transform. Slides: PPTX, PDF.
7. T 9/17: MP2 walk-through, and introduction to robotics.
8. R 9/19: Exam 1 Review
9. T 9/24: Exam 1 (in class)
10. R 9/26: Image filtering and Image features. PPTX, PDF. Optional supplementary material: derivation of the matched filter.
11. T 10/1: Integral Image filtering, and Adaboost. Video; powerpoint; pdf. Sample Problem about integral images, and its Solution. And here is the article that proposed the name "integral image" for this type of feature: Robust Real-Time Object Detection by Viola and Jones.
12. R 10/3: Image upsampling, downsampling, and interpolation. IPYNB, HTML. Sample Problems, Solution.
13. T 10/8: Speech Signals. MOV, WMV, MP4, Sample Problems, Solutions. (Optional extra material on windowed speech: MOV, MP4)
14. R 10/10: The LPC-10 Speech Coder; LPC Synthesis. powerpoint; pdf.
15. T 10/15: International Phonetic Alphabet. Spectrogram Reading
16. R 10/17: Exam 2 Review (Practice Exam and its Solutions.)
17. T 10/22: Exam 2
18. R 10/24: Hidden Markov Models. I'm going to deliver this lecture, this year, using the blackboard. The Rabiner tutorial article is the most useful reference.
19. Speech recognition details: (1) mapping tokens to types, (2) Gaussian surprisal, (3) scaled forward-backward algorithm, (4) Viterbi algorithm.
20. R 10/31: MP5 walk-through. PPTX, PDF.
21. T 11/5: Face animation by moving pixels.
22. R 11/7: Introduction to Artificial Neural Nets.
23. T 11/12: MP6 walk-through
24. R 11/14: Face Animation: State of the art/current methods (Kuangxiao Gu)
25. T 11/19: Recurrent Neural Nets. Slides, Sample Problems, Solutions.
26. R 11/21: LSTM.
27. T 11/26: Vacation
28. R 11/28: Vacation
29. T 12/3: Convolutional Neural Nets. Slides, Sample Problems, Solutions.
30. R 12/5: Simulated Annealing, Mini-Batch, Data Augmentation. Slides, a video about simulated annealing.
There is no new theory, in this lecture, that you need for the exam. You don't need to know about simulated annealing, or about mini-batch, or about data augmentation. However, the sample problem only covers (1) forward-prop, (2) knowledge-based design, and (3) back-prop training, so the sample problem is fair game for the exam. Here it is: Sample Problem, Solutions.
31. T 12/10: Exam 3 Review