Skip to content

Homework1 part2 for 賴筱婷,鄭乃嘉,周育潤,翁慶年 #6

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 3 commits into
base: master
Choose a base branch
from
Open

Homework1 part2 for 賴筱婷,鄭乃嘉,周育潤,翁慶年 #6

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
d8b2d09
Add files via upload
zenspam Oct 2, 2016
2ba4598
Add files via upload
zenspam Oct 2, 2016
d9dfe98
Update README.md
zenspam Oct 2, 2016
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Binary file added Dynamic Neural Turing Machine.pdf
View file
Open in desktop
Binary file not shown.
Binary file added HW1_Papers2.docx
View file
Open in desktop
Binary file not shown.
Binary file added LSTM_A Search Space Odyssey.pdf
View file
Open in desktop
Binary file not shown.
24 changes: 18 additions & 6 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,12 +1,24 @@
# Homework1 - Introduce a New NN with Memory
Please complete each homework for each team, and <br>
mention who contributed which parts in your report.
In this homework, we will summarize two papers related to NN with memory <br>
The papers include: <br>
1. LSTM: A Search Space Odyssey <br>
2. Dynamic Neural Turing Machine with Soft and Hard Addressing Schemes <br>

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



# Motivation
NN with Memory can potentially to be used to acompplish many AI related tasks: Reasoning, Decision Making, etc. <br>
Here are some related talks:<br>
* Sumit Chopra from Facebook. Reasoning, Attention and Memory <a href="https://drive.google.com/open?id=0B_wzP_JlVFcKbHdpYVdZMjg3eTBQd2F1OG9QZlVhOGJoX0dz">slides</a>
* Edward Grefenstette from Google DeepMind. Beyond Seq2Seq with Augmented RNNs <a href="https://drive.google.com/open?id=0B_wzP_JlVFcKYTFaTVFJN18tbmtkX2V0WEEtWXVSdDV4UHVZ">slides</a>
To have a more comprehensive and deeper understanding about the different variants of <br>
LSTM and the practical mathematical method applied on it, we go throgh two informative <br>
papers to get clear insight of this frontier research territory <br>

* LSTM: A Search Space Odyssey <a href="https://arxiv.org/abs/1503.04069">slides</a>
* Dynamic Neural Turing Machine with Soft and Hard Addressing Schemes <a href="https://arxiv.org/abs/1607.00036">slides</a>

# To-Do
* [+10] Please find a recent paper (2014-2015) which introduced a NN with memory.
Expand Down