Weekly Schedule

• Review Syllabus
• Intro to Intro to ML
• Intro to Python
• Setting up Python and GitHub

Class Materials:

• Slides
• Code

Recommended Readings:

• Intro to Python (DSAP: Chapters 2.1 - 2.3): [1]
• Git and GitHub: [1]
• Python for JS developers: [1] [2]

Recommended Videos:

• Signing up for GitHub and Creating a GitHub Organization: [1] [2]

Homework 01 | due: 2024/09/10 - 5PM

• Everything you've never wanted to know about lists... and were afraid to ask
• Data Analysis
• Some (Light) Statistics

Class Materials:

• Slides
• Code

Recommended Readings:

• Python Lists: [1] [2]
• List Slicing: [1] [2]
• Python Dicts/Objects: [1] [2]

Recommended Videos:

• Ten Python Functions: [1]

Homework 02 | due: 2024/09/17 - 5PM

• Data Structures for media
• Audio Representation, Analysis and Processing
• Matplotlib

Class Materials:

• Slides
• Code

Recommended Readings:

• Training a single AI model can emit as much carbon as five cars in their lifetimes: [1]
• Audio Representation (FMP: Chapter 1.3): [1]
• Audio Acquisition, Representation and Storage (MLAIVA: Chapter 2): [1]
• Matplotlib (DSAP: Chapter 2.6): [1]
• Pyplot: [1]

Homework 03 | due: 2024/09/24 - 5PM

• Audio Representation, Analysis and Processing

Class Materials:

• Slides
• Code

Recommended Readings:

• Time Domain Features (MSR: Chapter 2.3.1): [1]
• Fourier Analysis of Signals (FMP: Chapter 2.1): [1]

Homework 04 | due: 2024/10/01 - 5PM

• Image Representation, Processing and Analysis

Class Materials:

• Slides
• Code

Recommended Readings:

• Image and Video Acquisition, Representation and Storage (MLAIVA: Chapter 3): [1]
• Image Representation (DLVS: Chapter 1.4): [1]
• Image types and file formats (HOIPP: see link): [1]
• PIL: [1]

Homework 05 | due: 2024/10/08 - 5PM

• Image Representation, Processing and Analysis

Class Materials:

• Slides
• Code

Recommended Readings:

• Basic image manipulations (HOIPP: see link): [1]

Homework 06 | due: 2024/10/15 - 5PM

• Dataset Exploration
• Pandas & DataFrames
• Scaling & Encoding

Class Materials:

• Slides
• Code

Recommended Readings:

• Pandas (DSAP: Chapter 2.5): [1]
• Matplotlib (DSAP: Chapter 2.6): [1]
• Scaling & Encoding (DSAP: Chapter 4.6): [1]
• Pandas: Intro, Recipes and Cheatsheets: [1] [2]
• Pyplot: [1]

Homework 07 | due: 2024/10/29 - 5PM

• Supervised Learning
• Regression & Classification
• ML with Scikit-Learn

Class Materials:

• Slides
• Code

Recommended Readings:

• Intro to Machine Learning (DSAP: Chapter 3): [1]
• Regression (DSAP: Chapter 4.1 - 4.7): [1]
• Classification (DSAP: Chapter 6.1): [1]
• Random Forests (DSAP: Chapter 7.3): [1]
• Pandas: Intro, Recipes and Cheatsheets: [1] [2]

Homework 08 | due: 2024/11/05 - 5PM

• Un-Supervised Learning
• Distance Metrics
• Clustering & PCA

Class Materials:

• Slides
• Code

Recommended Readings:

• Distance and Similarity (DSAP: Chapter 3.8): [1]
• Clustering (DSAP: Chapter 5.1): [1]
• Dimensionality Problems (DSAP: Chapter 3.9): [1]
• Dimensionality Reduction and PCA (DSAP: Chapter 8.1 and 8.2): [1]
• Visualizing K-Means Clustering: [1]
• Secrets of PCA: A Comprehensive Guide to Principal Component Analysis: [1]

Recommended Videos:

• PCA Intro: [1]
• Advanced PCA Details: The Math and Some Tips: [1] [2]

Homework 09 | due: 2024/11/12 - 5PM

• PCA Review
• Evaluation Functions: Accuracy, Precision, Recall
• Confusion Matrix
• ML Review
• Intro to Neural Networks

Class Materials:

• Slides
• Code

Recommended Readings:

• Review: Choosing a Model: [1]
• Confusion Matrix (DSAP: Chapter 6.1.1): [1]
• Accuracy, Precision, Recall: [1]
• Machine Learning Basics (DL: Chapter 5): [1]
• Deep Learning and Neural Networks (DLVS: Chapter 2): [1]
• Programming and Math Preliminaries (D2L: Chapter 2): [1]

Homework 10 | due: 2024/11/19 - 5PM

• Neural Networks
• Tensors
• PyTorch

Class Materials:

• Slides
• Code

Recommended Readings:

• Tensors (DLPT: Chapters 3, 4.1 and 4.3): [1] [2]
• The Mechanics of Learning (DLPT: Chapter 5 and 6): [1] [2]
• A Recipe for Training Neural Networks: [1]
• Optimizers: [1] [2]

Recommended Videos:

• Tensor Basics: [1]

Homework 11 | due: 2024/11/26 - 5PM

• Image Neural Networks
• DataLoaders
• Normalizations

Class Materials:

• Slides
• Code

Recommended Readings:

• Fully-Connected Networks (DLPT: Chapter 7): [1]
• Regularization (DLPT: Chapter 8.5): [1]
• Datasets and DataLoaders: [1]
• More Regularization: [1] [2]
• A Recipe for Training Neural Networks: [1]
• Machine Learning for Artists (with TensorFlow): [1]
• Neural Network Playground: [1] [2]

Homework 12 | due: 2024/12/03 - 5PM

• Data Augmentation
• CNNs
• Finetuning

Class Materials:

• Slides
• Code

Recommended Readings:

• Learning from Images: Fully Connected and Convolutional Networks (DLPT: Chapters 7 and 8): [1] [2]
• Advanced CNN Architectures and Transfer Learning (DLVS: Chapters 5 and 6): [1] [2]
• Visualizing CNNs: [1] [2]
• More CNNs: [1] [2]

Homework 13 | due: 2024/12/10 - 5PM

• Other Image Networks: Style Transfer, Deep Dream
• Embeddings
• RNNs
• VAEs

Class Materials:

• Slides
• Code

Recommended Readings:

• DeepDream and Style Transfer (DLVS: Chapter 9): [1]
• Visual Embeddings (DLVS: Chapter 10): [1]
• Inceptionism: Going Deeper into Neural Networks: [1]

Homework 14 | due: 2024/12/17 - 5PM