|
|
| 第62行： |
第62行： |
| | *revise on the first version | | *revise on the first version |
| | |- | | |- |
| − | |Aiting Liu || || | + | |Aiting Liu || || *prepare diagrams in chapter3 |
| | |- | | |- |
| | |Shiyao Li || | | |Shiyao Li || |
| Date |
People |
Last Week |
This Week
|
| 2016/08/22
|
Yang Feng |
- surveyed the line of neural parsing work
- arranged the nlp wiki pages
- arranged the report of tensorflow
|
- start the work of neural grammar
|
| Jiyuan Zhang |
- added punctuation to input
- added input vector to the attention layer
- the result of the poem7_49k [here]
|
- writing books
- an overview of RNN,RBM,LSTM
|
| Aodong Li |
- Mainly focus on writing chapter 2, Linear Model.
- Now we have completed Introduction, Polynomial Regression, Linear Regression, Linear Classification, Probabilistic PCA, part of Probabilistic LDA.
|
- Complete the remaining of chapter 2--PLDA and Bayesian Approach.
|
| Andy Zhang |
- read books, papers, etc. about chapter3 neural networks;
- wrote the outine of this chapter
|
|
| Aiting Liu |
|
|
| Shiyao Li |
|
|
| 2016/08/29
|
Yang Feng |
- continued surveying the line of neural parsing work
- read papers of variants of RBM and neural Turing machine
- learned tensorflow
|
- read more papers of Turing machine and get the full picture of my idea
- start the baseline work of neural Turing machine
|
| Jiyuan Zhang |
- shared an overview of LSTM,RNN,RBM
- prepared relevant knowledge for writing book
- ran models of 58k-hybird and 14k-hybird [result]
|
- the main focus on writing books
|
| Aodong Li |
- Finish the first version of chapter 2, Linear Model
- Help Lantian for ICASSP
|
- Revise the Linear Model chapter (Waiting for teacher Wang's reply)
|
| Andy Zhang |
- almost finish the first version of chapter3
|
- hope to finish the first version before Sep 2nd, main challenge is to draw the pictures myself
- revise on the first version
|
| Aiting Liu |
|
*prepare diagrams in chapter3
|
| Shiyao Li |
- Prepare the presentation of Linear Algebra and Probability Theory and Information Theory
- start to learn tensorflow
|
- learn some models by tensorflow
|
