Lec # Date Topics
0 27 August 2019 Introduction (PDF)
1 29 August 2019 Overview of Machine Learning and Imaging (PDF)
2 29 September 2019 Continuous Mathematics Review (PDF)
3 3 September 2019 From Continuous to Discrete Mathematics (PDF)
4 5 September 2019 Discrete Functions (PDF)
5 10 September 2019 Introduction to Optimization (PDF)
6 12 September 2019 Ingredients for Machine Learning (PDF)
7 17-19 September 2019 Linear and Logistic Classification (PDF)
8 24 September 2019 “Deep” Networks: theoretical motvation (PDF)
9 26 Sept, 1 Oct 2019 Convolutional Neural Networks (PDF)
10 3 Oct 2019 Backpropagation in Deep Networks (PDF)
11 8 Oct 2019 Tools for your Deep Learning Toolbox (PDF)
12 10 Oct 2019 CNN implementation and visualization (PDF)
13 17 Oct 2019 CNN visualization tools and extensions (PDF)
14a 22 Oct 2019 CNNs for object detection and segmentation(PDF)
14b 24 Oct 2019 CNNs as Autoencoders (PDF)
15 24 Oct 2019 Introduction to Physical Layers in Machine Learning (PDF)
16 29 Oct 2019 Examples of Physical Layers in CNNs (PDF)
17 31 Oct 2019 Introduction to Fourier Optics (PDF)
18 5 Nov 2019 Physical Layers with Coherent Fields (PDF)
19 7 Nov 2019 Physical Layer Guidelines and Implementations (PDF)
20 12 Nov 2019 Published Physical CNN Examples and Ethics (PDF)
21 14 Nov 2019 Recurrent Neural Networks (PDF)
22 19 Nov 2019 Reinforcement Learning (PDF)

Lecture Resources

  1. Jupyter Notebook: Tensorflow basic optimization example
  2. Jupyter Notebook: High level intro to Neural Networks in Tensorflow
  3. Jupyter Notebook: A simple Autoencoder in Tensorflow/Keras
  4. Jupyter Notebook: Weighted image sum example
  5. Jupyter Notebook: Physical layers exmaple