esehara

# -*- coding: utf-8 -*-
from gensim.models import word2vec
import MeCab
import random
model = word2vec.Word2Vec.load("oogiri_gensim.model")
tagger = MeCab.Tagger("-Ochasen")

def word_and_kind_parse(line):
    line_word = line.split("\t")
    if len(line_word) < 2:

Bollegala

"""
This program compares ADAM vs AdaGrad. You can modify the function f and its gradient grad_f 
in the code, run the two algorithms and compare their convergence. For the simple function
f(x1, x2) = (x1 - 2) ** 2 + (x1 + 3) ** 2, (alpha = 0.1 and tolerence 1e-3)
AdaGrad converged at 2023 iterations, whereas ADAM required only 83!
"""

import numpy

raine

[alias]
  grep-add = "!sh -c 'git ls-files -m -o --exclude-standard | grep $1 | xargs git add' -"
  grep-add-patch = "!sh -c 'git add -p `git ls-files -m -o --exclude-standard | grep $1`' -"

neubig

#!/usr/bin/env python
# -*- coding: utf-8 -*-

# This is a simplified implementation of the LSTM language model (by Graham Neubig)
#
#  LSTM Neural Networks for Language Modeling
#  Martin Sundermeyer, Ralf Schlüter, Hermann Ney
#  InterSpeech 2012
# 
# The structure of the model is extremely simple. At every time step we

rezoo

Caffe tutorial

この文章ではCNN実装であるCaffeを用いて，特徴ベクトルの抽出やパラメータの学習を行うための方法について説明する．

Caffeでサポートされている機能

以下の作業を行いたいのであれば，Caffeを用いることが望ましい．

• CNNを利用した画像の多クラス分類
• CNNによる特徴ベクトルの抽出
• CNNの転移学習
• Stacked Auto Encoder

Mekajiki

package net.mekajiki;

import com.ibm.icu.text.Transliterator;
import java.util.ArrayList;
import java.util.List;

public class Hiragana2Phoneme {
    public static String hiragana2Phoneme(String text) {
        return romaji2Phoneme(hiragana2Romaji(text));
    }

aflc

// Copyright (c) 2013 Hiroyuki Tanaka
// Released under the MIT license

#include <stdint.h>
#include <cstdlib>
#include <cstring>
#include <string>
#include <map>
#include <vector>
#include <iostream>

crowdmatt

{
"IAB1": "Arts & Entertainment",
"IAB1-1": "Books & Literature",
"IAB1-2": "Celebrity Fan/Gossip",
"IAB1-3": "Fine Art",
"IAB1-4": "Humor",
"IAB1-5": "Movies",
"IAB1-6": "Music",
"IAB1-7": "Television",
"IAB2": "Automotive",

ttezel

#A Collection of NLP notes

##N-grams

###Calculating unigram probabilities:

P( w_i ) = count ( w_i ) ) / count ( total number of words )

In english..

stober

#! /usr/bin/env python
"""
Author: Jeremy M. Stober
Program: SOFTMAX.PY
Date: Wednesday, February 29 2012
Description: Simple softmax function.
"""

import numpy as np
npa = np.array