青空朗読 | 青空文庫に所蔵されている本を朗読しています

http://aozoraroudoku.jp/

「青空朗読」はインターネット上の図書館である「青空文庫」に掲載されている本を朗読する ...

「青空文庫」を朗読した mp3 をダウンロードできる。
この音声データと「青空文庫」のテキストを合わせれば、日本語音声コーパスとして使えるだろう。

ディープラーニング チュートリアル（もしくは研究動向報告）

http://www.vision.is.tohoku.ac.jp/index.php/download_file/view/15/137/

岡谷貴之　齋藤真樹
東北大学

日本語のスライド。

DeepLearning.University – An Annotated Deep Learning Bibliography | Memkite

http://memkite.com/deep-learning-bibliography/

Links to Deep Learning Subtopics

深層学習のリンク集。

[1504.00941] A Simple Way to Initialize Recurrent Networks of Rectified Linear Units

http://arxiv.org/abs/1504.00941

In this paper, we propose a simpler solution that use recurrent neural networks composed of rectified linear units.

Key to our solution is the use of the identity matrix or its scaled version to initialize the recurrent weight matrix.

再帰ネットに ReLU (rectified linear units) を使って長期の時間的構造を学習する。

Learning a Deep Convolutional Network for Image Super-Resolution

http://mmlab.ie.cuhk.edu.hk/projects/SRCNN.html

Test code for SRCNN

SRCNN のソースコードがある。

[1501.00092] Image Super-Resolution Using Deep Convolutional Networks

http://arxiv.org/abs/1501.00092

The mapping is represented as a deep convolutional neural network (CNN) that takes the low-resolution image as the input and outputs the high-resolution one.

畳み込みニューラルネットを使って、低解像度の画像を入力して高解像度の画像を出力する。

Random Ponderings: A Brief Overview of Deep Learning

http://yyue.blogspot.ca/2015/01/a-brief-overview-of-deep-learning.html

(This is a guest post by Ilya Sutskever on the intuition behind deep learning as well as some very useful practical advice. Many thanks to Ilya for such a heroic effort!)

Stanford University CS231n: Course Projects Winter 2015

http://cs231n.stanford.edu/reports.html

CS231n: Convolutional Neural Networks for Visual Recognition

CS231n Course Project Reports

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