Columbia University E6894, Spring 2017 (7:00-9:30pm, Wednesday, 627 Seeley W. Mudd Building)

Deep Learning for Computer Vision, Speech, and Language

The computing resource is endorsed by Paperspace and Google Cloud


(Note: please use Google group to ask questions)
  • Liangliang Cao (liangliang.cao_at_gmai)
  • Xiaodong Cui (
  • Kapil Thadani (
  • Guest lecturer: Markus Nussbaum-Thom (
  • Guest lecturer: Nikolai Yakovenko (
  • Guest lecturer: Shiyu Chang (

Teaching Assistants

(Note: please use Google group to raise questions)
  • Chad DeChant (
  • Yizhou Wang (

Office hour

Every Wednesday at 6:15 on the 6th floor of Mudd
Or contact Chad ( to schedule.

Course Introduction

This graduate level research class focuses on deep learning techniques for vision, speech and natural language processing problems. It gives an overview of the various deep learning models and techniques, and surveys recent advances in the related fields.

This course uses Keras and theano as the primary programminging tool. However, other toolkits including Tensorflow, Torch, Caffe, MxNet, PaddlePaddle are also welcome. GPU programming experiences are preferred although not required.

Frequent paper presentations and a heavy programming workload are expected.


  • 60% project
  • 30% homework and paper presentation
  • 10% participation


This course received generous supports from Paperspace,, Skycatch, and Google cloud.
Liangliang Cao Updated 03/15/2017