- The paper describes an unsupervised approach to train a generic, distributed sentence encoder.
- It also describes a vocabulary expansion method to encode words not seen at training time.
- Link to the paper
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Go to github | |
Create new repository [don't need to initialize with the readme (can add later)] | |
Go to R Studio | |
File -> New Project -> Version Control -> Git | |
Ctrl+V repository URL from GitHub | |
File -> New -> Markdown, enter Title, etc. | |
In the Markdown window, change "output=html_document" to "output=github_document" | |
Knit the document for the first time, will prompt you to save | |
Save as Title.rmd | |
In the "git" tab of the R studio Environment window, you will notice that the knit produced: |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
// ==UserScript== | |
// @name Github html preview | |
// @author https://github.com/vaniakosmos | |
// @version 1.0 | |
// @description Shortcut for htmlpreview.github.io | |
// @match https://github.com/**/*.html | |
// @grant none | |
// @require http://code.jquery.com/jquery-3.2.1.min.js | |
// ==/UserScript== |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
titanic_1tree = h2o.gbm(x = predictors, y = response, | |
training_frame = titanicHex, | |
ntrees = 1, min_rows = 1, sample_rate = 1, col_sample_rate = 1, | |
max_depth = 5, | |
# use early stopping once the validation AUC doesn't improve by at least 0.01% | |
# for 5 consecutive scoring events | |
stopping_rounds = 3, stopping_tolerance = 0.01, | |
stopping_metric = "AUC", | |
seed = 1) |