thereadme/sibe
1
0
Fork 0
Code Issues 1 Pull Requests Projects Releases Wiki Activity

chore(readme): word2vec chart explained

Browse Source
This commit is contained in:
Mahdi Dibaiee 2016-10-01 12:32:08 +03:30
parent 85971bc84d
commit 56fded810a
1 changed files with 28 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
README.md
View File

@ -67,3 +67,31 @@ notMNIST dataset, sigmoid hidden layer, cross-entropy loss, learning rate decay
notMNIST dataset, relu hidden layer, cross-entropy loss, learning rate decay and sgd ([`notmnist.hs`](https://github.com/mdibaiee/sibe/blob/master/examples/notmnist.hs)):
![notMNIST](https://github.com/mdibaiee/sibe/blob/master/notmnist.png?raw=true)
### Word2Vec
word2vec on a very small sample text:
```
the king loves the queen
the queen loves the king,
the dwarf hates the king
the queen hates the dwarf
the dwarf poisons the king
the dwarf poisons the queen
the man loves the woman
the woman loves the man,
the thief hates the man
the woman hates the thief
the thief robs the man
the thief robs the woman
```
The computed vectors are transformed to two dimensions using SVD:
`king` and `queen` have a relation with `man` and `woman`, `love` and `hate` are close to each other,
and `dwarf` and `thief` have a relation with `poisons` and `robs`, also, `dwarf` is close to `queen` and `king` while
`thief` is closer to `man` and `woman`. `the` doesn't relate to anything.
![word2vec results](https://raw.githubusercontent.com/mdibaiee/sibe/master/w2v.png)
This is a very small dataset and I have to test it on larger datasets.