CS 490/590 - Intro to Neural Networks and Deep Learning
2023 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: Applications of Deep Learning
Tentative schedule is provided below – assignments dates and lectures will be updated as the course progresses.
UNIT 1: Introduction to Deep Learning and Machine Learning
UNIT 2: Fundamentals of Neural Networks
| WEEK 5 |
| L6: Backpropagation |
| R6: Backpropagation |
| T2: Multiclass Classification with PyTorch T3: BackpropagationT3: Backprop Derivation Solution |
| V4: Grad Descent for Neural Nets V5: Backprop Logic V6: Forward & Backpropagation |
| V7: Mini-batch Grad Descent V8: Mini-batch Grad Descent Logic |
| WEEK 6 |
| HW1: Linear Regression (Due: Tue 2/21 (W7) via Bb)PROJECT PROPOSAL (Due: Fri 3/03 (W8) via Bb) |
| Backpropagation continued |
| WEEK 7 |
| HW2: Backprop and Multiclass Classification (Due: Tue 2/28 (W8) via Bb) |
| L7: Distributed Representations R7: Distributed Representations |
| V9: Distributed Representations |
| Project Ideation Check-in |
| WEEK 8 |
| L8: Optimization L9: Generalization |
| R8: Optimization R9: Generalization R10: Autodiff |
| Extra Tutorial: Autodiff w/ Autograd & PyTorch |
| V10: Generalization IV11: Generalization II V12: Optimization - Momentum |
| MIDPOINT PRESENTATION (Due: Thu 3/30 (W12) via Bb)MIDPOINT REPORT (Due: Fri 3/31 (W12) via Bb) |
| WEEK 9 |
| SPRING BREAK |