BME 646 and ECE 60146

Deep Learning

by

Avi Kak   and   Charles Bouman


Spring 2025

PREREQUISITES FOR THIS CLASS

In order to do well in this class, you must be proficient in programming with Python. Beyond that, all that is required for you to enroll in this class is that you be a graduate student in engineering, computer science, quantitative psychology, mathematics, etc.



Piazza: link


Click Here for the Homework Problems and Their Two Best Solutions for Previous Offerings of This Class


Click Here for Old Exams and Solutions


Week 1   Tuesday,  Jan 9: Course Intro (Bouman) [Slides] and Theory Lecture Syllabus (Bouman) [Slides],
  and Python OO for DL (Kak) [Slides]    [Python OO updated: Jan 16, 2024]

  Thursday, Jan 11: (Bouman) [slides] What is machine learning? Single layer neural networks
  and the MSE loss function

Week 2   Tuesday,  Jan 16: (Kak) [slides] Torchvision and Random Tensors    [updated: January 16, 2024]

  Thursday, Jan 18: (Bouman) [Slides] Gradient descent optimization; Calculation of gradient;
  matrix interpretation of gradient

  (Some of the Torchvision related material during this week will be illustrated with the functionality built into the
   YOLOLogic module that you can access by clicking here.)
Week 3   Tuesday,  Jan 23:  (Kak) [Slides] Autograd for Automatic Differentiation and Auto-Construction
  of Computational Graphs    [updated: January 28, 2024]

  Thursday, Jan 25: (Bouman) [slides] Intro to ML: Tensors; GD for single layer NNs; Local and
  global minima

  (Several of the key ideas used for automatic differentiation in Autograd will be explained with the help of the
   ComputationalGraphPrimer module that you can access by clicking here.)      [updated to Version 1.1.4: January 28, 2024]
Week 4   Tuesday,   Jan 30: (Kak) [slides] A First Introduction to Torch.nn for Designing Deep Networks
  and to DLStudio for Experimenting with Them    [updated: January 25, 2024]

  Thursday, Feb 1:  (Bouman) [Slides] Optimization of deep functions; GD on acyclic graphs;
  General loss functions

  (We will talk about torch.nn with the help of the DLStudio module that you can access by clicking here.)
Week 5   Tuesday,  Feb 6: (Kak) [slides] Demystifying the Convolutions in PyTorch    [updated: February 6, 2024]

  Thursday, Feb 8:: (Bouman) [slides] Convolutional NNs; Adjoint gradient for CNNs
Week 6   Tuesday,  Feb 13: (Kak) [slides] Using Skip Connections to Mitigate the Problem of Vanishing Gradients,
  and Using Batch, Instance, and Layer Normalizations for Improved SGD in Deep Networks     [updated: February 17, 2024]

  Thursday, Feb 15: (Bouman) [slides] Probability and estimation; Frequentist vs Bayesian estimation;
  bias variance tradeoff


  (The material related to Kak's lecture on skip connections will be explained with the help an in-class demo based on the
   inner class SkipConnections of the DLStudio module that you can access by clicking here.)
Week 7   Tuesday,  Feb 20:   (Kak) [slides] Multi-Instance Object Detection -- Image Cells and Anchor Boxes
   [updated: February 20, 2024]

  Thursday, Feb 22: (Bouman) [Slides] Training and Generalization; Regularization and dropout methods

  (Multi-instance object detection and localization is much more difficult problem compared to the case when you have a single object
   in an image. Such problems are solved with the help of image cells and anchor boxes. This lecture introduces you to these concepts.
   My code for explaining these ideas is in Version 2.1.1 of my YOLOLogic module that you can access by clicking here.)
Week 8   Tuesday,  Feb 27: (Kak) [slides] Transpose Convolutions and the Encoder-Decoder Architectures for
  Semantic Segmentation of Images    [updated: September 19, 2024]

  Thursday, Feb 29: (Bouman) Mid-Term Test 1 ( exams )


  (The material related to semantic segmentation is based on the nUnet network which is my implementation of the Unet. You will find the
   code for mUnet in my DLStudio module that you can access by clicking here.)
Week 9   Tuesday,  March 5: (Kak) [slides] Metric Learning with Deep Neural Networks     [posted: March 5, 2024]

  Thursday, March 7:   (Bouman) [slides] Stochastic gradient descent; Batches and epochs;
  Learning rate and momenturn; ADAM optimization
Week 10               Spring Break
Week 11   Tuesday,  March 19: (Kak) [Slides] Generative Data Modeling with Networks Based on Adversarial
   Learning and Denoising Diffusion
[updated: March 26, 2024]

  Thursday, March 21: (Bouman) [slides] Batch normalization; Positional encoding; NeRFs

  (The lecture by Kak on Generative Modeling will be explained with the help of demos based on the code in DLStudio's AdversarialLearning
  and Diffusion modules that you can access by clicking here.)
Week 12   Tuesday,  March 26: (Kak) [Slides] Recurrent Neural Networks for Text Classification and Data Prediction
  [updated: April 2, 2024]

  Thursday, March 28: (Bouman) [slides] Recurrent Neural Networks, LSTM, GRU; Unsupervised Learning
   and Autoencoders

  (The material related to text classification is based on the TEXTnet, TEXTnetOrder2, and GRUnet networks of the DLStudio
   that you can access by clicking here.)
Week 13   Tuesday,  April 2: (Kak) [Slides] Word Embeddings and Sequence-to-Sequence Learning     [updated: April 2, 2024]

  Thursday, April 4: (Bouman) [slides] Adversarial Learning, generators and discriminators, generative
   adversarial networks, and Nash equilibrium.
Week 14   Tuesday,  April 9: (Kak) [Slides] Transformers: Learning with Purely Attention Based Networks
  [updated: May 4, 2024]

  Thursday, April 11: (Bouman) [slides] GAN convergence, theory and practice; Wasserstein GANs;
   and Conditional GANs
Week 15   Tuesday,  April 16: (Kak) [slides] Transformer Based Learning for BERT and GPT Language Models
  [updated: October 23, 2024]

  Thursday, April 18: (Bouman) Mid-Term Test 2 ( exams )
Week 16   Tuesday,  April 23: (Kak) [Slides] Reinforcement Learning: Incorporating Human Preferences in the
  Fine-Tuning of Large Language Models
   [updated: April 23, 2024]

  Thursday, April 25: (Bouman) [slides] Generative diffusion models, and DALL-E generative diffusion
  models


Links to the documentation pages you will be visiting frequently:

- DLStudio    [updated: May 1, 2024]
- ComputationalGraphPrimer    [updated: January 28, 2024]
- YOLOLogic    [updated: February 28, 2024]
- Master documentation page for PyTorch
- A direct link to the torch.nn module
- Torchvision Datasets
- Master documentation page for Torchvision
- A direct link to Torchvision Transforms
- Master documentation page for Torchtext
- A useful summary of many of the most basic operations on PyTorch Tensors
- The homepage for CIFAR-10 and CIFAR-100 image datasets

Recommended Books:

- The Principles of Deep Learning Theory
- https://www.manning.com/books/grokking-deep-learning
- Deep Learning
- Neural Networks and Deep Learning
- Data Science from Scratch
- Python Machine Learning
- http://machinelearningmastery.com/deep-learning-courses/
- Pytorch tutorials

Recommended Supplementary Course Material:

- CMU deep learning
- Stanford Class by FeiFei and Karpathy. For videos
- Udacity Deep Learning nano-degree

Valid HTML 4.01 Transitional Valid CSS!