“Xingchao work”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
Date Line
第36行: 第36行:
 
:2. Write Binary Vector for theano mode.
 
:2. Write Binary Vector for theano mode.
 
:3. Thinking the method for merge different resource for one matrix factorization process.
 
:3. Thinking the method for merge different resource for one matrix factorization process.
  <Written by 10-12>
+
====Done====
 +
:1. Test different matrix factorization lost functions.
 +
:2. Write Binary Vector for theano mode.
 +
:3. Thinking the method for merge different resource for one matrix factorization process.
 +
  <Written by 10-13>
 +
 
 +
===Date 2015-10-13===
 +
====Plan to do====
 +
:1. Read Papers for matrix factorization.
 +
:2. Read Papers for binary vectors.
 +
====Done====
 +
:1. Read Papers for matrix factorization.
 +
    Paper list:
 +
      Neural Word Embedding as Implicit Matrix Factorization. Omer Levy;
 +
:2. Read Papers for binary vectors.
 +
    Paper list:
 +
      Learning to Hash for Indexing Big Data - A Survey. Jun Wang;
 +
      Learning Hash Codes with Listwise Supervision. Jun Wang;
 +
      Kernelized Locality-Sensitive Hashing for Scalable Image Search. Brian Kulis;
 +
<Written by 10-14>
 +
 
 +
===Date 2015-10-13===
 +
====Plan to do====
 +
:1. Read Papers for matrix factorization.
 +
:2. Read Papers for binary vectors.
 
====Done====
 
====Done====

2015年10月14日 (三) 10:59的版本

Chaos Work

Date Line

Date 2015-10-09

Plan to do

1. Write Matrix Factorization program.
2. Write DNN Max-Margin program with dropout.
3. Run some test model in GPU machines.
<Written by 10-08>

Done

2. Write DNN Max-Margin program with dropout.
3. Run some test model in GPU machines.


Date 2015-10-10

Plan to do

1. Write Matrix Factorization program.
2. Start test different matrix factorization lost functions.
3. Write Binary Vector for theano mode.
<Written by 10-09>

Done

1. Write Matrix Factorization program.
2. Start test different matrix factorization lost functions.

<Written by 10-12>

Date 2015-10-12

Plan to do

1. Test different matrix factorization lost functions.
2. Write Binary Vector for theano mode.
3. Thinking the method for merge different resource for one matrix factorization process.

Done

1. Test different matrix factorization lost functions.
2. Write Binary Vector for theano mode.
3. Thinking the method for merge different resource for one matrix factorization process.
<Written by 10-13>

Date 2015-10-13

Plan to do

1. Read Papers for matrix factorization.
2. Read Papers for binary vectors.

Done

1. Read Papers for matrix factorization.
   Paper list:
     Neural Word Embedding as Implicit Matrix Factorization. Omer Levy;
2. Read Papers for binary vectors.
   Paper list:
     Learning to Hash for Indexing Big Data - A Survey. Jun Wang;
     Learning Hash Codes with Listwise Supervision. Jun Wang;
     Kernelized Locality-Sensitive Hashing for Scalable Image Search. Brian Kulis;
<Written by 10-14>

Date 2015-10-13

Plan to do

1. Read Papers for matrix factorization.
2. Read Papers for binary vectors.

Done