PhD : recommended resources
If you are interested in doing a PhD or pre-PhD research internship in Computer Vision and Machine Learning, please see below for recommended learning resources. Please note that much of this is advanced graduate text and initially you need to read selectively (such as introductory chapters) to get a feel for the subject and techniques. Also, search for "introduction to .." or "tutorial on .." for more basic resources on core topics.
Back to PhD applicants page.
Computer Vision books
- Computer Vision : A Modern Approach : Forsyth and Ponce
- Computer Vision: Algorithms and Applications, Richard Szeliski
- Multiple View Geometry in Computer Vision : Hartley and Zisserman
- Introductory techniques for 3D Computer Vision : Trucco and Verri
- 3D Imaging, Applications and Analysis : Pears, Liu, and Bunting.
Machine Learning Online Courses and Resources
Machine Learning books
- Pattern Recognition and Machine Learning, Chris Bishop
- Pattern Classification, Duda Hart and Stork
- Machine Learning : A Probabilistic Perspective : Kevin Murphy
- The Elements of Statistical Learning: Hastie, T., Tibshirani, R., and R. Friedman
- Pattern Recognition and Neural Networks, Ripley
Background knowledge : linear algebra, optimisation
Introduction to deep learning
- First of the CNN YouTube video series by Andrew Ng
- Excellent introductory YouTube video by Chris Olah
- Excellent CNN introductory YouTube video by Brandon Rohrer
- Neural Networks and Deep Learning, by Michael Nielsen. (A very accessible introduction.)
- Deep Learning, by Ian Goodfellow, Yoshua Bengio and Aaron Courville. (Excellent self-contained and widely-read book.)
- Introduction (to Deep Learning book) Video introduction (to deep learning) presented by Ian Goodfellow.
Two minute paper series (YouTube), by Karoly Zsolnai-Feher.
These are good motivational overviews: here are a few examples, there are many more in this series.
Recurrent networks (a bit more specialized for time series data)
Short machine learning lessons, by mathematicalmonk (YouTube), the first three ...
Useful concepts for dealing with 3D point clouds and meshes
Nick Pears