Lectures
You can download the lectures here. We will try to upload lectures prior to their corresponding classes.
-
Introduction
tl;dr:
[Slides]
Suggested Readings:
- Lab
- HMST Chapter 1 and Chapter 2
- ML Project check list
- NumPy tutorial
- Colab tutorial
- Kaggle tutorial
- Video for NumPy
- Video for Colab/Kaggle
- [Recorded video]
-
Framing the problem and constructing the dataset
tl;dr:
[Slides]
Suggested Readings:
- Lab
- HMST Chapter 1
- Data-centric AI
- Snorkel
- CROWDLAB
- [Recorded video]
-
NO CLASS (228 Peace Memorial Day)
tl;dr:
-
Database and Data Wrangling
tl;dr:
[Slides]
Suggested Readings:
- Lab
- HMST Chapter 1
- SQL cheatsheet
- Pandas cheatsheet
- [Recorded video]
-
-
Feature selection and extraction
tl;dr:
[Slides]
Suggested Readings:
- Lab
- How to Choose a Feature Selection Method For Machine Learning
- HMST Chapter 8, 9
- [Recorded video]
-
-
-
The deep learning journey
tl;dr:
[Slides]
Suggested Readings:
- Lab_tf
- Lab_torch
- NN Playground
- HMST Chpater 10, 11
- [Recorded video]
-
Image processing with Convolutional Neural Networks
tl;dr:
[Slides]
Suggested Readings:
- Lab_tf
- Lab_pytorch
- CNN explainer
- Image kernels
- HMST Chpater 14
- [Recorded video]
-
Sequence processing using Recurrent Neural Network
tl;dr:
[Slides]
Suggested Readings:
- Lab
- AttentionViz
- BertViz
- HMST Chpater 15, 16
- [Recorded video]
-
Transfer learning and self-supervised learning
tl;dr:
[Slides]
Suggested Readings:
- Lab
- HMST Chpater 11, 14
- [Recorded video]
-
Representation and generative learning
tl;dr:
[Slides]
Suggested Readings:
- Lab
- HMST Chpater 17
- GAN Lab
- Difussion Explainer
- [Recorded video]
-
Hyperparamter search and experiment management
tl;dr:
[Slides]
Suggested Readings:
- Lab
- HMST Chpater 19
- Exploring Bayesian Optimization
- [Recorded video]