CS 490/590 - Intro to DL and ML
2022 Spring
An introduction to the basic ideas and techniques underlying deep neural networks and machine learning.
Table of contents
- UNIT 1: Introduction to Deep Learning and Machine Learning
- UNIT 2: Fundamentals of Neural Networks
- UNIT 3: Advanced Applications of Deep Learning
UNIT 1: Introduction to Deep Learning and Machine Learning
| WEEK 1 (Tue 1/11) |
| L1: Introduction |
| R1: Introduction |
| WEEK 2 (Tue 1/18) |
| L2: Linear Algebra L2: Probability |
| R2: Linear AlgebraR2: Probability |
| Link: Stanford Numpy Tutorial V1: Numpy Video |
| WEEK 3 (Tue 1/25) |
| L3-4: Linear Models |
| R3: Linear RegressionR3: Linear ClassifiersR3: Training a Classifier |
| T1a: Classification T1b: REgression |
| HW1: Linear Regression (Due: Mon 2/7 via Bb) |
| V2: Gradient Descent I V3: Gradient Descent II |
| WEEK 4 (Tue 2/01) |
| RECAP AND HOMEWORK REVIEW |
| Link: DL Cheatsheet |
UNIT 2: Fundamentals of Neural Networks
| WEEK 9 |
| SPRING BREAK |
UNIT 3: Advanced Applications of Deep Learning
| WEEK 10 (Tue 3/15) |
| CNNs REVIEW |
| MIDPOINT PRESENTATION (Due: Mon 4/11 via Bb)MIDPOINT REPORT (Due: Fri 4/15 via Bb) |
| OLD EXAMS: i) 2014, ii) 2015a(soln), 2015b(soln), iii) 2017a, 2017b, a & b solns, iv) 2018a, 2018b, a & b solns |
| WEEK 11 (Tue 3/22) |
| EXAM REVIEW |
| WEEK 12 (Tue 3/29) |
| MIDTERM EXAM on (Thu 3/31) |
| WEEK 13 (Tue 4/05) |
| L13: Recurrent Neural Nets L14: LSTMs |
| R13: CNNs R14: LSTMs |
| T6: RNNsT6: RNNs Companion SlidesT6: Tips for Report Slides |
| HW3: Understanding CNNs (Due: Mon 3/18 via Bb) |
| V19: Distributed RepresentationsV20: Training RNNsV21: RNN Toy Example |
| V22: RNN GradientsV23: LSTMs |
| FINAL POSTER (Due: Thu 4/28 via Bb)FINAL REPORT (Due: Tue 5/03 via Bb) |
| WEEK 14 (Tue 4/12) |
| HW4: RNN Backprop (Due: Fri 3/29 via Bb) |
| Midpoint Presentations |
| WEEK 15 (Tue 4/19) |
| L15: VAEs |
| R15: Auto-Encoding Variational Bayes |
| T7: VAEs |
| V24: Kingma: Auto-Encoding Variational Bayes |
| WEEK 16 (Tue 4/26) |
| WEEK 17 |
| FINALS WEEK |