Homework1 - Introduce a New NN with Memory

In this homework, we will summarize two papers related to NN with memory
The papers include:

1. LSTM: A Search Space Odyssey
   
2. Dynamic Neural Turing Machine with Soft and Hard Addressing Schemes
   

負責部份:

1. LSTM: A Search Space Odyssey:
   Organizer:周育潤, 翁慶年
   
2. Dynamic Neural Turing Machine with Soft and Hard Addressing Schemes
   Organizer:鄭乃嘉, 賴筱婷
   

Motivation

To have a more comprehensive and deeper understanding about the different variants of
LSTM and the practical mathematical method applied on it, we go throgh two informative
papers to get clear insight of this frontier research territory

• LSTM: A Search Space Odyssey slides
• Dynamic Neural Turing Machine with Soft and Hard Addressing Schemes slides

To-Do

• [+10] Please find a recent paper (2014-2015) which introduced a NN with memory.
• [+50] Write a report to briefly introduce the paper;
• [+40] then, focus on discussing the unique properties of the new NN and where it can be applied to take advantage of the properties.

Candidates

• Search RNN on Arxiv-sanity link
• Jianpeng Cheng et al. Long Short-Term Memory-Networks for Machine Reading. arXiv16’.
• Nal Kalchbrenner et al. Grid Long Short-Term Memory. arXiv16’. (From DeepMind, Alex)
• Kaisheng Yao et al. Depth-Gated LSTM. arXiv15’.
• Shuohang Wang et al. Learning Natural Language Inference with LSTM. arXiv15’.
• Junyoung Chung et al. Gated Feedback Recurrent Neural Networks. arXiv15’.

Other

• Due on Oct. 3rd before class.