DeepLearn 2017

Here are the slides for DeepLearn 2017.

For background reading, you may find the following course materials helpfu:

The "classic books" I mentioned are:
  • Duda and Hart: Pattern Classification
  • Jae Lim: Two dimensional signal processing
  • Gonzales and Woods: Digital Image Processing
  • Berger: Statistical Decision Theory
  • Minsky and Papert: Perceptrons
  • Horn: Robot Vision
  • Strang: Introduction to Applied Mathematics


Selected Open Source Projects

Deep Learning and Computer Vision

OCRopus OCR An open source OCR system with competitive recognition performance. Written in Python and C/C++. Currently handles Latin script and Fraktur.

CLSTM An open source C++-based LSTM and deep learning implementation, primarily with applications to OCR.

RAST Globally optimal geometric matching.

Image Understanding Library (iulib) A C++ library for image processing from the late 80's and early 90's.

Bindings / Wrappers

PyOpenFST A Python wrapper around the OpenFST library.

Selected Lectures

Lectures and lecture notes generally come with many iPython Notebooks allowing people to experiment with the concepts discussed in class.

Learning and Perception (introductory undergraduate course in pattern recognition and image processing) 

Neural Computation and Self Organization (introductory graduate course in neural computing, machine learning, and related topics)

Natural Language Processing and Applications (graduate course mostly on statistical NLP and some information retrieval)

Document and Content Analysis (graduate course on OCR, document analysis, handwriting recognition)

Foundations and Frontiers of Artificial Intelligence (graduate course on the theory, philosophy, biology of intelligence)

Privacy, Identity and Computational Forensics (graduate course on using computational methods in forensics)

Multimedia Information Retrieval (graduate course on object recognition, multimedia databases, computer vision)

Other Information

LinkedIn

CV (not entirely up to date)

Bio

Thomas Breuel works on deep learning and computer vision at NVIDIA Research. Prior to NVIDIA, he was a full professor of computer science at the University of Kaiserslautern (Germany) and worked as a researcher at Google, Xerox PARC, the IBM Almaden Research Center, IDIAP, Switzerland, as well as a consultant to the US Bureau of the Census. He is an alumnus of the Massachusetts Institute of Technology and Harvard University.