Unsupervised Feature Learning and Deep Learning Tutorial

http://ufldl.stanford.edu/tutorial/

Description: This tutorial will teach you the main ideas of Unsupervised Feature Learning and Deep Learning.

ディープ・ラーニングだけではなく、多層ニューラルネットなどの基礎技術の解説もある。

[1502.02551] Deep Learning with Limited Numerical Precision

http://arxiv.org/abs/1502.02551

Our results show that deep networks can be trained using only 16-bit wide fixed-point number representation when using stochastic rounding, and incur little to no degradation in the classification accuracy.

16ビットの浮動小数点数（半精度浮動小数点数）でも確率的に丸め処理をすれば使い物になるらしい。

GTC 2015 - Googleが「ディープラーニング」に対する取り組みを紹介 | マイナビニュース

http://news.mynavi.jp/articles/2015/03/20/gtc02/

Long short term memory - Wikipedia, the free encyclopedia

http://en.wikipedia.org/wiki/Long_short_term_memory

Long short term memory (LSTM) is a recurrent neural network (RNN) architecture

[1503.04069] LSTM: A Search Space Odyssey

http://arxiv.org/abs/1503.04069

• The most commonly used LSTM architecture (vanilla LSTM) performs reasonably well on various datasets and using any of eight possible modifications does not significantly improve the LSTM performance.
• Certain modifications such as coupling the input and forget gates or removing peephole connections simplify LSTM without significantly hurting performance.
• The forget gate and the output activation function are the critical components of the LSTM block. While the first is crucial for LSTM performance, the second is necessary whenever the cell state is unbounded.

CS231n Convolutional Neural Networks for Visual Recognition

http://cs231n.github.io/

These notes accompany the Stanford CS class CS231n: Convolutional Neural Networks for Visual Recognition.

Stanford University CS231n: Convolutional Neural Networks for Visual Recognition

http://vision.stanford.edu/teaching/cs231n/

Rectifier (neural networks) - Wikipedia, the free encyclopedia

http://en.wikipedia.org/wiki/Rectifier_%28neural_networks%29#Leaky_ReLUs

Leaky ReLUs allow a small, non-zero gradient when the unit is not active.

CIFAR-10 Competition Winners: Interviews with Dr. Ben Graham, Phil Culliton, & Zygmunt Zając | no free hunch

http://blog.kaggle.com/2015/01/02/cifar-10-competition-winners-interviews-with-dr-ben-graham-phil-culliton-zygmunt-zajac/

The "MP" entries above denote max pooling, and "VeryLeakyReLU" denotes a "leaky" ReLU with a fairly large (alpha was 0.33) non-zero gradient.

[1412.6980] Adam: A Method for Stochastic Optimization

http://arxiv.org/abs/1412.6980

We introduce Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions.

意思決定を行う脳の組織構造 | 沖縄科学技術大学院大学 OIST

https://www.oist.jp/ja/news-center/news/2015/2/26/18669

腹側線条体は、ラットが試行をいつ開始するかを決める早い段階で最も活性化しました。背内側線条体では、左右いずれかの穴に向かう前、左右の選択の結果得られる報酬の予測に応じて発火レベルが変化しました。背外側線条体は、試行の様々なタイミングで短い発火を示し、細かな運動制御に関係していると考えられます。

DEEP LEARNING An MIT Press book in preparation

http://www-labs.iro.umontreal.ca/~bengioy/dlbook/

An MIT Press book in preparation
Yoshua Bengio, Ian Goodfellow and Aaron Courville

GeoLite2 Free Downloadable Databases « Maxmind Developer Site

http://dev.maxmind.com/geoip/geoip2/geolite2/

GeoLite2 databases are free IP geolocation databases comparable to, but less accurate than, MaxMind’s GeoIP2 databases. GeoLite2 databases are updated on the first Tuesday of each month.

IPアドレスと国名、街の名前、経度・緯度のデータベース。

GeoLite Legacy Downloadable Databases « Maxmind Developer Site

http://dev.maxmind.com/geoip/legacy/geolite/

The GeoLite databases are our free IP geolocation databases. They are updated on the first Tuesday of each month. These databases are offered in the same binary and csv formats as our subscription databases. Any code which can read the subscription databases can also read the GeoLite databases.

IPアドレスと国名、街の名前、経度・緯度、AS番号のデータベース。

Huffman coding (Java) | Project Nayuki

http://www.nayuki.io/page/huffman-coding-java

Huffman coding (Java)

This project is an open-source reference implementation of Huffman coding in Java. The code is intended to be used for study, and as a solid basis for modification and extension. As such, it is optimized for clear logic and low complexity, not speed/memory/performance.

Overview of the TAC 2008 Update Summarization Task

http://www.nist.gov/tac/publications/2008/additional.papers/update_summ_overview08.proceedings.pdf

Abstract
The summarization track at the Text Analysis
Conference (TAC) is a direct continuation
of the Document Understanding
Conference (DUC) series of workshops,
focused on providing common data and
evaluation framework for research in automatic
summarization.

自動要約アルゴリズムを公開しました！ | カメリオ開発者ブログ

http://aial.shiroyagi.co.jp/2013/08/%E3%82%B7%E3%83%B3%E3%83%97%E3%83%AB%E3%81%A0%E3%81%91%E3%81%A9%E3%83%91%E3%83%AF%E3%83%95%E3%83%AB%E3%81%AA%E8%87%AA%E5%8B%95%E8%A6%81%E7%B4%84%E3%82%A2%E3%83%AB%E3%82%B4%E3%83%AA%E3%82%BA%E3%83%A0/

要点から言うと、この度試験的に自動要約サービスを公開しました。

実行ファイルとDLLを一つにまとめる

http://qiita.com/krsak/items/75a257cc0866a7e8e4aa

Visual C# で、自作のクラスライブラリと実行ファイルを一つにまとめる（静的リンクもどきを行う）やり方です。
Microsoftが提供しているツール「ILMerge」で複数のアセンブリを一つのアセンブリにマージできます。
このツールを使うことで、自作のクラスライブラリのDLLと実行ファイルを一つにまとめることができます。

Kaggle CIFAR-10の話 - デー

http://ultraist.hatenablog.com/entry/2014/11/08/192646

• 学習データを36倍に増化(Data Augmentation)
• GCN + ZCA Whiteningで正規化
• VGGのモデルをベースにしたConvolutional Neural Network(CNN)を学習
• 上記のモデルを重みの初期値とMini-Batch-SGDの更新順を変えて6個学習し、各分類器の平均を予測として出力

乱択データ構造の最新事情 －MinHash と HyperLogLog の最近の進歩－

http://www.slideshare.net/iwiwi/minhash

MinHash, b-bit MinHash, HyperLogLog, Odd Sketch, HIP Estimator の解説です