Skip to content

Instantly share code, notes, and snippets.

View kepler's full-sized avatar
🎯
Focusing

Fabio Natanael Kepler kepler

🎯
Focusing
View GitHub Profile
@mranney
mranney / emoji_sad.txt
Created January 30, 2012 23:05
Why we can't process Emoji anymore
From: Chris DeSalvo <chris.desalvo@voxer.com>
Subject: Why we can't process Emoji anymore
Date: Thu, 12 Jan 2012 18:49:20 -0800
Message-Id: <AE459007-DF2E-4E41-B7A4-FA5C2A83025F@voxer.com>
--Apple-Mail=_6DEAA046-886A-4A03-8508-6FD077D18F8B
Content-Transfer-Encoding: quoted-printable
Content-Type: text/plain;
charset=utf-8
@kepler
kepler / vlngram.py
Created February 7, 2013 00:00
Variable length n-gram markov chain for sequence learning.
"""
Fabio N. Kepler, Sergio L. S. Mergen, Cleo Z. Billa, Jose C. Bins
2012
First written for the PAutomaC Competition, 2012.
Check URL for file format details.
(http://ai.cs.umbc.edu/icgi2012/challenge/Pautomac)
You are free to use it. We would like if you let us know (kepler@unipampa.edu.br).
@karpathy
karpathy / gist:587454dc0146a6ae21fc
Last active July 11, 2024 10:36
An efficient, batched LSTM.
"""
This is a batched LSTM forward and backward pass
"""
import numpy as np
import code
class LSTM:
@staticmethod
def init(input_size, hidden_size, fancy_forget_bias_init = 3):