Columbia University EECS E6894, Spring 2015

Deep Learning for Computer Vision and Natural Language Processing

Google Group

This Google group is the place students can discuss their projects or questions related to this course.


Toolkits used in this class
  • Theano (required)
  • Caffe: (suggested for large scale CV although not required)
  • iPython notebook: (suggested as the Python editor in the team collaboration, although you are free to choose other IDEs like Eclipse, pycharm, or pyscripter, etc.)
Theano resources Computing resources Deep Learning for computer vision
  • Caffe: the most popular opensource project on cv+deep learning
  • Torch7 (with a nice iTorch interface): widely used in Facebook and NYU
  • CUDA-convnet2: excellent GPU programming with multi-GPU supports, less user-friendly
  • CCV: a compact c package
Toolkits for speech and language GPU programming and fast CNN


You may find a lot of challenges with training/testing datasets on Kaggle. But the following come from traditional academic researchers.

CoNLL shared tasks & datasets over the years (including a variety of NLP tasks): Other NLP resources
  • Parsing:
  • Semantic relation extraction:
  • Information extraction: (requires LDC membership)
  • Information extraction:
  • Paraphrase
  • Paraphrase
  • Question answering
  • Machine translation:
Image with captions/text Image classification Live Image Classification Challenges Faces and OCRs Large scale image and video datasets (you may probably need powerful GPUs if you want to try them)

Related Deep Learning courses and resource

Liangliang Cao and James Fan, Updated 02/14/2015