Mercurial > hg > tvii
comparison README.txt @ 64:2adeb95cf4d5
add more useful software + an idea
author | Jeff Hammel <k0scist@gmail.com> |
---|---|
date | Sun, 17 Dec 2017 12:41:26 -0800 |
parents | 38fe99071b11 |
children |
comparison
equal
deleted
inserted
replaced
63:b911a7c01727 | 64:2adeb95cf4d5 |
---|---|
1 tvii | 1 tvii |
2 ==== | 2 ==== |
3 | 3 |
4 TV2 : more experiments in machine learning | 4 TV2 : experiments in machine learning |
5 | 5 |
6 | 6 |
7 Dependencies | 7 Dependencies |
8 ------------ | 8 ------------ |
9 | 9 |
19 and or `libhdf5-dev`. For `scipy` you need Lapack. | 19 and or `libhdf5-dev`. For `scipy` you need Lapack. |
20 | 20 |
21 You may install these with python 3.6 using:: | 21 You may install these with python 3.6 using:: |
22 | 22 |
23 pip install -e . | 23 pip install -e . |
24 | |
25 | |
26 Useful links + software | |
27 ----------------------- | |
28 | |
29 - [tensorflow](https://www.tensorflow.org/) | |
30 * [Parsey McParseface](https://github.com/tensorflow/models/tree/master/syntaxnet#using-the-pre-trained-nlp-models) (SyntaxNet) | |
31 - [torch](http://torch.ch/) | |
32 - [spaCy](https://spacy.io/) (NLP) | |
33 - [NakedTensor] (https://github.com/jostmey/NakedTensor) : Bare bone examples of machine learning in TensorFlow | |
34 - [Keras](https://keras.io/) : Keras is a high-level neural networks API, written in Python and capable of running on top of TensorFlow, CNTK, or Theano | |
35 - [Caffe](http://caffe.berkeleyvision.org/) | |
36 - [PaddlePaddle](http://doc.paddlepaddle.org/release_doc/0.9.0/doc/introduction/index.html): PaddlePaddle is a deep learning platform open-sourced by Baidu | |
37 | |
38 | |
39 Ideas | |
40 ----- | |
41 | |
42 * Given: a corpus of text, for a given acronym, yield | |
43 what it stands for (Bonus points: likely error rate and other | |
44 high-value matches) | |
45 | |
24 | 46 |
25 Links | 47 Links |
26 ----- | 48 ----- |
27 | 49 |
28 Things to check out: | 50 Things to check out: |
41 ---- | 63 ---- |
42 | 64 |
43 Jeff Hammel | 65 Jeff Hammel |
44 | 66 |
45 http://k0s.org/hg/tvii | 67 http://k0s.org/hg/tvii |
46 |