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

Deep Learning for Computer Vision, Speech, and Language

Final report due

Final project report will be due on midnight of May 7th. (No late submission will be accepted)
Rules for final project presentation and report.


Idol Awards

Idol award is given to the project which received most votes after presentation.
Idol Award Winner Hassan Akbari and Himani Arora
Speech Reconstruction from Silent Lip Movement Video
Idol Award Run-Up Emily Hua, Kelly Chen, and Wendy Wang
Mixlingual Automatic Speech Recognition

Final Projects

Final project presentation will be at 750 Schapiro CEPSR, 7-10pm April 26th.
1 Anthony Alvarez, Elsbeth Turcan, Fei-Tzin Lee
Style Transfer on Text
2 Emly Hua, Kelly Chen, Wendy Wang
Mixlingual ASR
3 Richard Godden, Yogesh Garg
Music style transfer
4 Ignacio Aranguren, Rahul Rana, Xiaoxue Du
Deep learning in Finance
5 Wenxi Chen, Wei Zhang
YOLOv2 on Tensorflow
6 Anshul Sachet, Yanglu Piao, GwonJae Cho
GIF upscaling
7 Mingyang Zheng, Lingyu Zhang
3D Semantic image segmentation for scene parsing
8 Xiang Hua, Ruixuan Zhang
Multilingual image caption for searching
9 SunMao, YuZheng
10 Hassan Akbari, Himani Arora
Speech reconstruction from silent video
11 Yu Chun Chien, Chen-Yu Yen
Finding Sea Lions
12 Apoorv Kulshreshtha, Samarth Tripathi
Duplicate Qs prediction
13 Harish Shanker, Akshay Khatri
Language Modeling for Large Vocabularies
14 Zixiaofan Yang, Xing Lan
Emotion recognition in speech
15 Pabl Vicente Juan, Jose Vicente Ruiz Cepeda
GANs: From audio to image
16 Abhishek Jindal, Siddarth Varia, Oscar Chang
Ideintifying duplicate Quora Questions
17 Jonathan Koss, Manu Gandham
Crabgrass Classification

Midterm Report

Short midterm reports are available here.