Sujit Pal sujitpal
sujitpal
/ babi_memnn.py
Last active
October 3, 2016 01:21
My modified version of keras/examples/babi_memnn.py using the new functional API instead of Sequential API (changes between comment lines "construct network" and "compile network"). Originally driven by keras issue 3927.
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
| '''Trains a memory network on the bAbI dataset. | |
| References: | |
| - Jason Weston, Antoine Bordes, Sumit Chopra, Tomas Mikolov, Alexander M. Rush, | |
| "Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks", | |
| http://arxiv.org/abs/1502.05698 | |
| - Sainbayar Sukhbaatar, Arthur Szlam, Jason Weston, Rob Fergus, | |
| "End-To-End Memory Networks", | |
| http://arxiv.org/abs/1503.08895 |
sujitpal
/ alice_lstm_seq2seq.ipynb
Created
May 12, 2016 15:21
LSTM for Sequence to Sequence Generation - Deep Learning Learners Meetup Presentation May-12-2016
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
sujitpal
/ alice_chargen_rnn.ipynb
Created
May 12, 2016 15:19
RNN for Character Generation - Deep Learning Learners Meetup Presentation May-12-2016
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
sujitpal
/ junit_opennlp_extract_np_from_text.java
Created
April 24, 2016 17:15
JUnit/OpenNLP code to extract Noun Phrases from text. Originally from my pastebin (http://pastebin.com/bUDY7fb0).
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
| @Test | |
| public void testNounPhraseExtractionStandalone() throws Exception { | |
| SentenceDetectorME sentenceDetector; | |
| TokenizerME tokenizer; | |
| POSTaggerME posTagger; | |
| ChunkerME chunker; | |
| InputStream smis = null; | |
| InputStream tmis = null; | |
| InputStream pmis = null; | |
| InputStream cmis = null; |
sujitpal
/ wmd_short_sentences_scala.html
Created
April 24, 2016 16:41
Databricks HTML export of Scala Notebook for computing Word Mover's Distance for Similarity between Short Sentences.
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
| <!DOCTYPE html> | |
| <html> | |
| <head> | |
| <meta name="databricks-html-version" content="1"> | |
| <title>wmd_short_sentences - Databricks</title> | |
| <meta charset="utf-8"> | |
| <meta name="google" content="notranslate"> | |
| <meta http-equiv="Content-Language" content="en"> | |
| <meta http-equiv="Content-Type" content="text/html; charset=UTF8"> |
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
| #! /bin/sh | |
| ### BEGIN INIT INFO | |
| # Provides: redis-server | |
| # Required-Start: $remote_fs $syslog | |
| # Required-Stop: $remote_fs $syslog | |
| # Default-Start: 2 3 4 5 | |
| # Default-Stop: 0 1 6 | |
| # Short-Description: Start and stop redis-server | |
| ### END INIT INFO |
sujitpal
/ cms_benefits_data_analysis.ipynb
Created
April 28, 2014 22:24
Basic Data Analysis of Medicaid Benefits data from CMS.gov
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
sujitpal
/ cms_data_download.ipynb
Created
April 28, 2014 22:23
Some simple Python code to parse the CMS.gov site and extract links to all the dataset zips.
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
sujitpal
/ lung_cancer_data_analysis.ipynb
Last active
August 29, 2015 13:57
Using Correlation Coefficients to select most predictive Gene Expressions in Lung Cancer Data
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
sujitpal
/ big_data_kids_pres.ipynb
Created
March 8, 2014 23:57
Presentation to demonstrate using Hadoop Streaming and Python to group/collect and join/exclude operations on Database data.
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
NewerOlder