Kyle Kastner kastnerkyle
kastnerkyle
/ Minimal Character Model.ipynb
Created
May 18, 2017 02:01
— forked from kylemcdonald/Minimal Character Model.ipynb
Minimal character-level language model in Python. Always picks the same prediction from equally probably predictions.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
kastnerkyle
/ tweet_dumper.py
Created
May 19, 2017 19:09
— forked from yanofsky/LICENSE
A script to download all of a user's tweets into a csv
This file contains hidden or 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
| #!/usr/bin/env python | |
| # encoding: utf-8 | |
| import tweepy #https://github.com/tweepy/tweepy | |
| import csv | |
| #Twitter API credentials | |
| consumer_key = "" | |
| consumer_secret = "" | |
| access_key = "" |
kastnerkyle
/ pytorch+char-rnn.ipynb
Created
May 26, 2017 16:21
— forked from kylemcdonald/pytorch+char-rnn.ipynb
Recreating char-rnn from the spro/practical-pytorch tutorials.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
kastnerkyle
/ Adversarial variational bayes toy example.ipynb
Created
June 14, 2017 14:25
— forked from poolio/Adversarial variational bayes toy example.ipynb
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
kastnerkyle
/ Adversarial variational bayes toy example.ipynb
Created
June 14, 2017 14:25
— forked from poolio/Adversarial variational bayes toy example.ipynb
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
kastnerkyle
/ check_ordinal.py
Created
June 26, 2017 19:30
— forked from fabianp/check_ordinal.py
Check that the gradient of the ordinal logistic regression is correct
This file contains hidden or 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
| """ | |
| Check that the gradient of the logistic regression is correct | |
| """ | |
| import numpy as np | |
| BIG = 1e12 | |
| def phi(t): | |
| """ |
kastnerkyle
/ yellow_fin.py
Created
July 4, 2017 11:46
— forked from botev/run_yellow_fin_vae.py
Theano Yellow Fin
This file contains hidden or 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
| import numpy as np | |
| import theano | |
| import theano.tensor as T | |
| from theano.printing import Print | |
| from collections import OrderedDict | |
| def yellow_fin(loss, params, beta=0.99, | |
| learning_rate_init=0.01, momentum_init=0.0, | |
| t=None, window_width=20, debug=False): |
kastnerkyle
/ how-to-make-a-racist-ai-without-really-trying.ipynb
Created
July 27, 2017 16:52
— forked from rspeer/how-to-make-a-racist-ai-without-really-trying.ipynb
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
kastnerkyle
/ mini_sequence_labeler.py
Created
August 22, 2017 12:56
— forked from kyunghyuncho/mini_sequence_labeler.py
PyTorch implementation of a sequence labeler (POS taggger).
This file contains hidden or 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
| """ | |
| PyTorch implementation of a sequence labeler (POS taggger). | |
| Basic architecture: | |
| - take words | |
| - run though bidirectional GRU | |
| - predict labels one word at a time (left to right), using a recurrent neural network "decoder" | |
| The decoder updates hidden state based on: | |
| - most recent word |
kastnerkyle
/ 2017 Fantasy Football Projections.ipynb
Created
September 4, 2017 01:57
— forked from seanjtaylor/2017 Fantasy Football Projections.ipynb
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.