Deep Learning for Computer Vision: 2. Convolutional Neural Nets

This is the second in a series of two videos taken from lectures given at the University of Cambridge in December, 2023. They act as an introduction to deep learning in the context of computer vision, providing both background on the underlying technology and an overview of common applications explained at an undergraduate level. No prior experience with machine learning or AI is required.

First lecture: https://youtu.be/LDcBRixd0jQ
Second lecture: https://youtu.be/HfX_IOn5wjA

GPU Canny Edge Detection Demo: https://matajoh.github.io/canny/

The Polo video segment was sourced from the West Ham Polo Club: https://www.youtube.com/watch?v=D3VCSd7AlYs

You can find a GitHub repo with additional learning and revision resources here: https://github.com/matajoh/dl_for_computer_vision

These lectures were given as part of Engineering Tripos Part IIB, 4F12: Computer Vision: http://teaching.eng.cam.ac.uk/content/engineering-tripos-part-iib-4f12-computer-vision-2023-24.

The following is a list of articles and papers on which these lectures are based and which can provide further reading. Where possible, I've attempted to include a link to the online version of the content:

1. Robust physical-world attacks on deep learning visual classification: https://github.com/evtimovi/robust_physical_perturbations
2. ResNet: https://en.wikipedia.org/wiki/Residual_neural_network
3. LFW Dataset: https://vis-www.cs.umass.edu/lfw/
4. Batch normalization: https://en.wikipedia.org/wiki/Batch_normalization
5. Adam optimizer: https://en.wikipedia.org/wiki/Stochastic_gradient_descent#Adam
6. Variational autoencoder: https://en.wikipedia.org/wiki/Variational_autoencoder
7. AlexNet: https://en.wikipedia.org/wiki/AlexNet
8. Lin et al. Network in network. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2013.
9. COCO dataset: https://cocodataset.org/#home
10. Long, J. et al. Fully convolutional networks for semantic segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(4):640–651, 2017.
11. McCulloch, W. S. and Pitts, W. A logical calculus of the ideas immanent in nervous activity. Bulletin of Mathematical Biophysics, 5:115–133, 1943.
12. Olazaran, M. A sociological study of the official history of the perceptrons controversy. Social Studies of Science, 26(3):611–659, 1996.
13. YOLO: https://github.com/ultralytics/yolov5
14. Rosenblatt, F. The perceptron: A probabilistic model for information storage and organization in the brain. Psychological Review, 65:386–408, 1958.
15. FaceNet: https://en.wikipedia.org/wiki/FaceNet
16. Werbos, P. Beyond Regression: New Tools for Prediction and Analysis in the Behavioral Sciences. PhD thesis, Harvard University, 1974.

Видео Deep Learning for Computer Vision: 2. Convolutional Neural Nets канала Matthew Johnson