취향저격한 구독 상품을 한눈에 모아보고 알림받는 내구독 북마크한 콘텐트와 내활동을 아카이빙하는 보관함 기억하고 싶은 문구를 스크랩하고 기록하는 하이라이트/메모 중앙일보 회원에게만 제공되는 스페셜 콘텐트
１枚の紙から切り出したペーパークラフト
취향저격한 구독 상품을 한눈에 모아보고 알림받는 내구독 북마크한 콘텐트와 내활동을 아카이빙하는 보관함 기억하고 싶은 문구를 스크랩하고 기록하는 하이라이트/메모 중앙일보 회원에게만 제공되는 스페셜 콘텐트
New Guide on Creating an App & Making Money | Bilue
Experience Design Mobile Apps Cloud Engineering Enterprise Integrations Web Development Smart TV Contact Us Why Mobile Apps?If you are reading this, then you have most likely heard of the app craze that has taken over in recent years. A record 218 billion apps were downloaded last year while consumer spending leaped 20% to hit $143 billion, for the first time. The need to create and make money wi
Equilibrium Propagation: Bridging the Gap Between Energy-Based Models and Backpropagation
We introduce Equilibrium Propagation, a learning framework for energy-based models. It involves only one kind of neural computation, performed in both the first phase (when the prediction is made) and the second phase of training (after the target or prediction error is revealed). Although this algorithm computes the gradient of an objective function just like Backpropagation, it does not need a s
Q&A: Andrew Ng, chief scientist, Chinese search giant Baidu
Artificial intelligence whiz Andrew Ng hangs his hat these days at a nondescript building in Sunnyvale that serves as the Silicon Valley outpost of the Chinese search giant Baidu. The modest digs belie Baidu’s big Asian footprint. With more than 600 million monthly active mobile users, it’s often referred to as “the Google of China.” Like Google, Baidu has been exploring artificial intelligence fo
Yahoo open-sources CaffeOnSpark deep learning framework for Hadoop
Yahoo open-sources CaffeOnSpark deep learning framework for Hadoop Yahoo today is releasing some key artificial intelligence software (AI) under an open-source license. The company last year built a library called CaffeOnSpark to perform a popular type of AI called “deep learning” on the vast swaths of data kept in its Hadoop open-source file system for storing big data. Now it’s becoming availabl
All you need is a good init
Layer-sequential unit-variance (LSUV) initialization - a simple method for weight initialization for deep net learning - is proposed. The method consists of the two steps. First, pre-initialize weights of each convolution or inner-product layer with orthonormal matrices. Second, proceed from the first to the final layer, normalizing the variance of the output of each layer to be equal to one. Expe
Deep Tracking: Seeing Beyond Seeing Using Recurrent Neural Networks
This paper presents to the best of our knowledge the first end-to-end object tracking approach which directly maps from raw sensor input to object tracks in sensor space without requiring any feature engineering or system identification in the form of plant or sensor models. Specifically, our system accepts a stream of raw sensor data at one end and, in real-time, produces an estimate of the entir
Convolutional Rectifier Networks as Generalized Tensor Decompositions
Convolutional rectifier networks, i.e. convolutional neural networks with rectified linear activation and max or average pooling, are the cornerstone of modern deep learning. However, despite their wide use and success, our theoretical understanding of the expressive properties that drive these networks is partial at best. On the other hand, we have a much firmer grasp of these issues in the world
Deep Reinforcement Learning from Self-Play in Imperfect-Information Games
Many real-world applications can be described as large-scale games of imperfect information. To deal with these challenging domains, prior work has focused on computing Nash equilibria in a handcrafted abstraction of the domain. In this paper we introduce the first scalable end-to-end approach to learning approximate Nash equilibria without prior domain knowledge. Our method combines fictitious se
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
Very deep convolutional networks have been central to the largest advances in image recognition performance in recent years. One example is the Inception architecture that has been shown to achieve very good performance at relatively low computational cost. Recently, the introduction of residual connections in conjunction with a more traditional architecture has yielded state-of-the-art performanc
Why are deep nets reversible: A simple theory, with implications for training
Generative models for deep learning are promising both to improve understanding of the model, and yield training methods requiring fewer labeled samples. Recent works use generative model approaches to produce the deep net's input given the value of a hidden layer several levels above. However, there is no accompanying "proof of correctness" for the generative model, showing that the feedforward d
深層学習に最適化したディープラーニング専用ワークステーション “Deep Station DK-1”を発売開始 | 株式会社UEI
深層学習に最適化したディープラーニング専用ワークステーション “Deep Station DK-1”を発売開始 株式会社UEI(以下：UEI、ヨミ：ユーイーアイ、本社：東京都文京区、代表取締役社長 兼 CEO：清水 亮)は、プリファードインフラストラクチャー社(PFI)が開発したオープンソースの深層学習フレームワーク ChainerをベースとしたGUIディープラーニング環境と、同ソフトウェアとUbuntu14.04をプリインストールした深層学習用ワークステーション、“Deep Station DK-1”の正式受注を開始します。 また、ご購入いただいた方を対象とした、ディープラーニングの基礎から実際のデータの入力・分析操作までを1日で学ぶことができる「深層学習ベーシックセミナー」と、Pythonによるより本格的なデータ操作、ならびにLSTMの学習まで体験することができる「深層学習スタンダード
Deep Learningによるハンドサイン画像認識デモ 解説 (第一回) - 技ラボ
「ビッグデータEXPO東京 2015春」に展示しました「Deep Learningを利用したハンドサイン画像認識のデモ」について、全三回に分けて解説します。 今回は第一回です。シリーズ概要とデモ全体の概要について解説します。 by NagasawaKazuki 2015/04/20 はじめに ISPは、2015年3月12日(木)、13日(金)にザ・プリンスパークタワー東京で開催された「ビッグデータEXPO 東京」に出展しました。 ブースでは「Deep Learningを利用したハンドサイン画像認識のデモ」と「Deep Learningスターターキット」を展示し、多くの方に来訪していただきました。 当日の様子とブース 本連載では、ブースで展示していました「Deep Learningを利用したハンドサイン画像認識のデモ」について、技術的な内容を含めて全三回に分けて解説します。 シリーズ構成 本
富士通研究所、時系列データを高精度に分析する新たなDeep Learning技術を開発 | IoTNEWS
2021-09-092016-02-16 富士通研究所、時系列データを高精度に分析する新たなDeep Learning技術を開発 株式会社富士通研究所は、IoTアプリケーションに活用が期待される、振動が激しく人による判別が困難な時系列データに対して高精度な解析を可能とするDeep Learning技術（注1）を開発したと発表した。 Deep Learning技術は、人工知能の発展におけるブレークスルーとして注目されており、画像や音声では極めて高い認識精度を達成している一方で、適用できるデータの種類は限られている。特にIoT機器などから得られる、人による判別も困難なほどの激しい振動の時系列データを精度よく自動的に分類することは困難だった。 今回、最先端数学を活用し、時系列データから幾何的な特徴を抽出することで、激しい振動の時系列データを高精度に分類することができるDeep Learning技
リリース、障害情報などのサービスのお知らせ
最新の人気エントリーの配信
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く
Cracking AWS Solution Architect Professional Certification
GitHub - icoxfog417/rnn_demo: Recurrent Neural Network Demo by PyBrain
http://vision.stanford.edu/teaching/cs231b_spring1415/slides/alexnet_tugce_kyunghee.pdf
https://kaigi.org/jsai/webprogram/2014/pdf/785.pdf
PFIセミナー2016/2/25：生成モデルのDeep Learning
GitHub - szcom/rnnlib: RNNLIB is a recurrent neural network library for sequence learning problems. Forked from Alex Graves work http://sourceforge.net/projects/rnnl/
