Computer Vision and Machine Learning Wiki

The Public Wiki of the Computer Vision and Machine Learning Group.

ML has never been easier to get started with as a Computer Scientist due to the prevalence and availability of large datasets and GPU hardware.

A surge in commercial and academic interest in the field of machine learning has spawned a plethora of frameworks such as Tensorflow that perform a lot of the heavy lifting for us with respect to implementing ML algorithms.

Without a proper understanding of the theory behind ML algorithms, debugging models derived from existing work, designing new models, and tuning their performance becomes an operation on a black box. In order to be successful in ML research you must strive to gain a deeper understanding into how and why the ML algorithms we have work the way they do, and through this gain intuition into how we should build and improve upon these methods.

---

Discussion Groups

We have three groups where the CS Vision research-group comes together formally to exchange ideas.

• Journal Club, where once or twice a month the Group congregates to hear a presentation on some topic.

• Reading Group, where every two weeks we read a chapter of a book.

• Algorithm Club, where we discuss a fundamental algorithm in machine learning or some new, novel technique in the news.

Demo Code

• Using Tensorflow 2.0 to train an MLP image classifier for images of handwritten digits.

Index

• README.md

  This page. The main index of the Wiki.

  • How to Find Papers Online.md

    A tutorial in finding literature and academic papers online without getting stuck behind a journal paywall.

  • Thesis Templates and Academic Writing Tutorial

    A consistently styled set of thesis templates structured in LaTeX, Google Docs, and MS Word. These documents also serve as a written tutorial on document structuring, best practices, and proper citation and attribution of external works.

  • Recommended Literature.md

    A list academic papers and literature pertaining to machine learning research that should be considered required reading for all students starting ML projects.

  • Programming Resources.md

    How to setup and configure the software, languages, packages, and environment to do ML research.

  • Jetson TX2.md

    Steps for installing and building useful software for use on NVidia Jetson TX2 devices.

  • Jupyter Notebook Cheatsheet.md

    A list of the most useful shortcuts in Jupyter Notebook and Jupyter Lab.

  • Datasets.md

    A curated list of interesting datasets and resources for finding datasets that are useful for machine learning and computer graphics projects.