Resources
To begin, here are some useful resources related to our class, organized loosely by topic:
Linear Algebra
- The Matrix Cookbook Link
- Introduction to Applied Linear Algebra, by Stephen Boyd and Lieven Vandenberghe - Stanford Link
- Linear Algebra, by Gil Strang - MIT Link
Optimization
- An introduction to conjugate gradient descent without all the pain Link
- Optimization Models and Applications, by Laurent El Ghaoui - UC Berkeley Link
- Linear Algebra and Optimization, by A. Moitra - MIT Link
- Optimization Methods, by Dimitris Bertsimas - MIT Link
Signals
- What is a Fourier Transform? (3b1b) Link
- What is a Convolution? (3b1b) Link
- Convolution in Image Processing - MIT x 3b1b Link
- Images are signals Link
- Fourier Transform and Applications - Stanford Link
- Discrete Fourier Transform (Reducible) Link
- Fourier Transform and Uncertainty Priciple Link
- First Principles of Computer Vision - Columbia Link
Machine Learning
- Learning from Data, Yaser S. Abu-Mostafa - Caltech Link
- Matrix Methods in Data Analysis, Signal Processing, and Machine Learning, by Gil Strang - MIT Link
- Neural Networks Explained (3b1b) Link
Convolutional Neural Networks
Optics
- J. Goodman’s Introduction to Fourier Optics Link
Related Research Topics
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.
-
Slides from Data Driven Computational Imaging workshop at CVPR 2019. (Courtsey of Camera Culture Group at MIT Media Lab)
-
Enhancing Spatial Resolution of Optical Microscopy Over a Large Field of View and Depth of Field
-
Multi-Resolution CNN and Knowledge Transfer for Candidate Classification in Lung Nodule Detection
-
Towards Simple, Generalizable Neural Networks with Universal Training for Low SWaP Hybrid Vision
-
Thyroid Cancer Malignancy Prediction From Whole Slide Cytopathology Images
-
Studying Very Low Resolution Recognition Using Deep Networks
-
Unsupervised content-preserving transformation for optical microscopy
-
Data-efficient and weakly supervised computational pathology on whole-slide images
-
Remote photonic detection of human senses using secondary speckle patterns
-
Pre-training on Grayscale ImageNet Improves Medical Image Classification
-
Fourier ptychographic microscopy image stack reconstruction using implicit neural representations
-
Digital staining in optical microscopy using deep learning – a review
-
Designing Optics and Algorithm for Ultra-Thin, High-Speed Lensless Cameras
-
DeepCGH: 3D computer generated holography using deep learning
-
Physics-Based Learned Design: Optimized Coded-Illumination for Quantitative Phase Imaging
-
All-optical image denoising using a diffractive visual processor
-
Ring Deconvolution Microscopy: An Exact Solution for Spatially-Varying Aberration Correction