To begin, here are some useful resources related to our class, organized loosely by topic:

Linear Algebra

  1. The Matrix Cookbook Link
  2. Introduction to Applied Linear Algebra, by Stephen Boyd and Lieven Vandenberghe - Stanford Link
  3. Linear Algebra, by Gil Strang - MIT Link

Optimization

  1. An introduction to conjugate gradient descent without all the pain Link
  2. Optimization Models and Applications, by Laurent El Ghaoui - UC Berkeley Link
  3. Linear Algebra and Optimization, by A. Moitra - MIT Link
  4. Optimization Methods, by Dimitris Bertsimas - MIT Link

Signals

  1. What is a Fourier Transform? (3b1b) Link
  2. What is a Convolution? (3b1b) Link
  3. Convolution in Image Processing - MIT x 3b1b Link
  4. Images are signals Link
  5. Fourier Transform and Applications - Stanford Link
  6. Discrete Fourier Transform (Reducible) Link
  7. Fourier Transform and Uncertainty Priciple Link
  8. First Principles of Computer Vision - Columbia Link

Machine Learning

  1. Learning from Data, Yaser S. Abu-Mostafa - Caltech Link
  2. Matrix Methods in Data Analysis, Signal Processing, and Machine Learning, by Gil Strang - MIT Link
  3. Neural Networks Explained (3b1b) Link

Convolutional Neural Networks

  1. CNN Explainer - A very nice interactive page Link
  2. The Deep Learning Book Link

Optics

  1. J. Goodman’s Introduction to Fourier Optics Link

Below are some research topics related to deep learning applied to images, as well as to the optimization of imaging systems to create “smart” cameras, microscopes, MRI scanners and the like.

  1. Slides from Data Driven Computational Imaging workshop at CVPR 2019. (Courtsey of Camera Culture Group at MIT Media Lab)

    Data-Driven Computational Imaging Survey,

    Visual Sensing Using Machine Learning

  2. Deep Learning in Medical Imaging: General Overview

  3. Enhancing Spatial Resolution of Optical Microscopy Over a Large Field of View and Depth of Field

  4. A Recipe for Training Neural Networks

  5. Multi-Resolution CNN and Knowledge Transfer for Candidate Classification in Lung Nodule Detection

  6. Towards Simple, Generalizable Neural Networks with Universal Training for Low SWaP Hybrid Vision

  7. Pre-training without Natural Images

  8. Thyroid Cancer Malignancy Prediction From Whole Slide Cytopathology Images

  9. Learning to Resize Images for Computer Vision Tasks

  10. Studying Very Low Resolution Recognition Using Deep Networks

  11. Unsupervised content-preserving transformation for optical microscopy

  12. Data-efficient and weakly supervised computational pathology on whole-slide images

  13. Remote photonic detection of human senses using secondary speckle patterns

  14. Pre-training on Grayscale ImageNet Improves Medical Image Classification

  15. Fourier ptychographic microscopy image stack reconstruction using implicit neural representations

  16. NeuWS: Neural wavefront shaping for Guidestar-free imaging through static and dynamic scattering media

  17. Real-time, deep-learning aided lensless microscope

  18. Digital staining in optical microscopy using deep learning – a review

  19. Local Conditional Neural Fields for Versatile and Generalizable Large-Scale Reconstructions in Computational Imaging

  20. Designing Optics and Algorithm for Ultra-Thin, High-Speed Lensless Cameras

  21. DeepCGH: 3D computer generated holography using deep learning

  22. Neural 3D Holography

  23. Microscopes are coming for your job

  24. Physics-Based Learned Design: Optimized Coded-Illumination for Quantitative Phase Imaging

  25. All-optical image denoising using a diffractive visual processor

  26. Physics-Informed Machine Learning for Computational Imaging

  27. Untrained networks for compressive lensless photography

  28. Deep learning for single-shot autofocus microscopy

  29. Ring Deconvolution Microscopy: An Exact Solution for Spatially-Varying Aberration Correction

  30. Geomteric Deep Optical Sensing (Review)