Lectures

You can download the lectures here. Big Thanks to Jordan Sanders for agreeing to take notes in class that I can post here.

• 

  Lecture 1 Course Introduction
  Description: We will go over course policies, a brief description and introduction
  [Notes]
  
• 

  Lecture 2 Singular Value Decomposition (SVD)
  Description: We will go over basics of SVD
  [Notes]
  

  Suggested Readings:

  • Readings 1
  • ImageCompression (Colab)
• 

  Lecture 3 Image Compression with SVD
  Description: We will explore image compression in python using SVD
  [Notes]
  

  Suggested Readings:

  • SVD:Demo
• 

  Lecture 4 Image Encoding
  Description: Here we will look at computation of bases matrix for face images
  [Notes]
  

  Suggested Readings:

  • Eigenfaces (Colab)
  • SVD example
• 

  Lecture 5 Principal Component Analysis (PCA)
  Description: Here we will discuss dimensionality reduction through SVD decomposition
  [Notes]
  

  Suggested Readings:

  • PCA (Colab)
  • Reading 1
• 

  Lecture 6 PCA II
  Description: Here we will continue our discussion on PCA
  [Notes]
  
• 

  Lecture 7 PCA III
  Description: We will conclude the discussion on PCA
  [Notes]
  
• 

  Lecture 8 Neural Networks
  Description: We will introduce the neural network model for deep learning
  [Notes]
  
• 

  Lecture 9 Autoencoders
  Description: We will introduce the concept of Autoencoders
  [Notes]
  

  Suggested Readings:

  • Autoencoders: Linear layers (Colab)
• 

  Lecture 10 Autoencoders II
  Description: We will discuss Autoencoders with linear and convolutional layers
  [Notes]
  

  Suggested Readings:

  • Autoencoders: Convolutional layers (Colab)
  • Reading 1
  • Reading 2
  • Reading 3
• 

  Lecture 12 Probabilistic PCA
  Description: We will start the discussion of generative models with Probabilistic PCA
  [Notes]
  
• 

  Lecture 13 Probabilistic PCA II
  Description: We will continue with Probabilistic PCA
  [Notes]
  

  Suggested Readings:

  • Probabilistic PCA (Colab)
  • Reading 1
• 

  Lecture 14 Probabilistic PCA III
  Description: We will conclude Probabilistic PCA with code implementation in python
  [Notes]
  
• 

  Lecture 15 Variational Autoencoders I
  Description: We will start with Variational Autoencoders
  [Notes]
  

  Suggested Readings:

  • Reading 1
• 

  Lecture 16 Variational Autoencoders II
  Description: We will continue discussing Variational Autoencoders
  [Notes]
  
• 

  Lecture 19 Variational Autoencoders III
  Description: We will continue discussing Variational Autoencoders
  [Notes]
  
• 

  Lecture 20 Variational Autoencoders IV
  Description: We will continue discussing Variational Autoencoders
  [Notes]
  

  Suggested Readings:

  • Variational Autoencoders: Factorized Cov (Colab)
• 

  Lecture 21 Variational Autoencoders V
  Description: We will be discussing Variational Autoencoders with full covariance matrix for the encoder
  [Notes]
  

  Suggested Readings:

  • Variational Autoencoders: Full cov (Colab)
• 

  Lecture 23 VAE conclusion
  Description: We will be concluding VAEs and we will also discuss working with custom datasets
  
  

  Suggested Readings:

  • Custom Datasets (Colab)
• 

  Lecture 24 Gradient Descent for Deep Learning I
  Description: We will be discussing the basics of deriving gradients for optimizing neural networks
  [Notes]
  
• 

  Lecture 25 Gradient Descent for Deep Learning II
  Description: We will be concluding the basic discussion on optimizing neural networks
  [Notes]
  
• 

  Lecture 26 Gradient Descent for Deep Learning III
  Description: We will implement a regression and classification neural network from scratch in python
  
  

  Suggested Readings:

  • Classification from scratch (Colab)
  • Regression from scratch (Colab)