Unsupervised Representation Learning by Predicting Image Rotations
Over the last years, deep convolutional neural networks (ConvNets) have transformed the field of computer vision thanks to their unparalleled capacity to learn high level semantic image features. However, in order to successfully learn those features, they usually require massive amounts of manually labeled data, which is both expensive and impractical to scale. Therefore, unsupervised semantic fe
【GTC2018】NVIDIA「GPU Technology Conference 2018」開幕「Quadro GV100」発表 | おなやみ通信
【座間9人の話題】白石被告「後悔とか申し訳ない気持ち一切ない」「最初から欲望の対象。大切な人たちとは線引きできている」
Bayesian Convolutional Neural Network with MCMC (using Tensorflow and Edward)
Bayesian Convolutional Neural Network with MCMC (using Tensorflow and Edward) import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data import os import edward as ed from edward.models import Bernoulli, Normal, Categorical,Empirical from edward.util import Progbar from keras.layers import Dense from scipy.misc import imsave import matplotlib.pyplot as plt from edward.util
Deep Learning Phase Segregation
Phase segregation, the process by which the components of a binary mixture spontaneously separate, is a key process in the evolution and design of many chemical, mechanical, and biological systems. In this work, we present a data-driven approach for the learning, modeling, and prediction of phase segregation. A direct mapping between an initially dispersed, immiscible binary fluid and the equilibr
失敗しないAI活用、変革を起こすポイント--NECのデジタルトランスフォーメーション
AIは導入するだけではなく、その運用方法が正しくなければ効果を生まない。NECが考えるビジネスを変革させる方法とは──。2月に開催した「CNET Japan Live 2018」で、NEC デジタル戦略本部 本部長の中尾敏康氏が"AIが加速するデジタルトランスフォーメーション〜お客様との共創事例〜"と題し講演した。 NECが考えるデジタルトランスフォーメーションとはなにか。デジタル技術を活かし、企業や産業、都市、人に活力を生み出すことだという。 中尾氏は「実世界でデータを取得し、"見える化"する。それを分析し、予測して的確に手を打つことがICT（Information and Communication Technology）の提供する部分。これにより、実世界のヒト・モノ・コトに新たな意味を加える。企業や都市をマネージする」と説明。「デジタルトランスフォーメーションは新しい技術ではない。I
Norm matters: efficient and accurate normalization schemes in deep networks
Over the past few years, Batch-Normalization has been commonly used in deep networks, allowing faster training and high performance for a wide variety of applications. However, the reasons behind its merits remained unanswered, with several shortcomings that hindered its use for certain tasks. In this work, we present a novel view on the purpose and function of normalization methods and weight-dec
Complex-YOLO: An Euler-Region-Proposal for Real-time 3D Object Detection on Point Clouds
11institutetext: Valeo Schalter und Sensoren GmbH†, Ilmenau University of Technology* 11email: {martin.simon,stefan.milz,karl.amende}@valeo.com 11email: horst-michael.gross@tu-ilmenau.de Complex-YOLO: An Euler-Region-Proposal for Real-time 3D Object Detection on Point Clouds Abstract Lidar based 3D object detection is inevitable for autonomous driving, because it directly links to environmental un
Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learning
Deep neural networks (DNNs) enable innovative applications of machine learning like image recognition, machine translation, or malware detection. However, deep learning is often criticized for its lack of robustness in adversarial settings (e.g., vulnerability to adversarial inputs) and general inability to rationalize its predictions. In this work, we exploit the structure of deep learning to ena
Averaging Weights Leads to Wider Optima and Better Generalization
Deep neural networks are typically trained by optimizing a loss function with an SGD variant, in conjunction with a decaying learning rate, until convergence. We show that simple averaging of multiple points along the trajectory of SGD, with a cyclical or constant learning rate, leads to better generalization than conventional training. We also show that this Stochastic Weight Averaging (SWA) proc
Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNN
Recurrent neural networks (RNNs) have been widely used for processing sequential data. However, RNNs are commonly difficult to train due to the well-known gradient vanishing and exploding problems and hard to learn long-term patterns. Long short-term memory (LSTM) and gated recurrent unit (GRU) were developed to address these problems, but the use of hyperbolic tangent and the sigmoid action funct
Google、画像をピクセル単位で把握し各オブジェクトに割り当てるセマンティックセグメンテーションCNNモデル「DeepLab-v3」オープンソース発表
Google、画像をピクセル単位で把握し各オブジェクトに割り当てるセマンティックセグメンテーションCNNモデル「DeepLab-v3」オープンソース発表 2018-03-13 Googleは、同社機械学習ライブラリTensorflow実装の画像セマンティックセグメンテーションdeep learningモデル「DeepLab-v3」をオープンソースにて発表しました。 GitHub:models/research/deeplab at master · tensorflow/models セマンティックセグメンテーションは、画像をピクセルレベルで把握し、各ピクセル１つひとつを画像内の各オブジェクト、例えば「道路」「空」「人」「犬」などのオブジェクトクラスに意味付けし割り当てることです。各オブジェクトの境界にあたる輪郭を正確に特定します。 今回発表されたDeepLab-v3は、前回のv2に比べ、
NIPS2017まとめのまとめ | moskomule log
After being extremely popular in the early 1990s, neural networks have fallen out of favor in research in the last 5 years. In 2000, it was even pointed out by the organizers of the Neural Information Processing System (NIPS) conference that the term “neural networks” in the submission title was negatively correlated with acceptance. In contrast, positive correlations were made with support vector
Solving Bongard Problems With Deep Learning
Bongard problmes are named after their inventor, Soviet computer scientist Mikhail Bongard, who was working on pattern recognition in the 1960s. He designed 100 of this puzzles, to be a good benchmark for pattern recognition abilities, and they seem to be challenging for both people and algorithms. Here is an example: Figure 1. Six images on the left conform to a rule, or a pattern, and the six im
Chainerは数多くの企業に支えられている！Preferred Networksこれまでの歴史 | AI専門ニュースメディア AINOW
こんにちは。AINOWのなっぴです。 機械学習ライブラリは何を使っていますか？ ライブラリの中でも代表的なものが“Chainer”ですね。 Chainerはオープンソースの深層学習プラットフォームで、国内でAI業界を牽引するPreferred Networksが中心となって開発しています。 今回は、Preferred Networksのこれまでの歴史を追いました。 どのような企業がどんな形でPFNに関わっているのか。一目でわかるようにPFNの沿革を画像でまとめました。 Preferred Networks これまでの歴史 編集後記 PFNがChainerを作っている会社、ということしか知らなかった人も多いのではないでしょうか？ 大会で優秀な成績を残していたり、DeNAと会社を設立していたりなど、意外なPFNの沿革がわかりました。 IT企業だけでなく、大手機械メーカーのファナックやトヨタ自動
How to build a deep learning model in 15 minutes
An open source framework for configuring, building, deploying and maintaining deep learning models in Python. As Instacart has grown, we’ve learned a few things the hard way. We’re open sourcing Lore, a framework to make machine learning approachable for Engineers and maintainable for Machine Learning Researchers. A common feeling in Machine Learning: Uhhh, this single sheet of paper does not tell
Deep learning in production with Keras, Redis, Flask, and Apache - PyImageSearch
APIs Deep Learning Keras and TensorFlow by Adrian Rosebrock on February 5, 2018 Shipping deep learning models to production is a non-trivial task. If you don’t believe me, take a second and look at the “tech giants” such as Amazon, Google, Microsoft, etc. — nearly all of them provide some method to ship your machine learning/deep learning models to production in the cloud. Going with a model deplo
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
ゼロから始める深層強化学習（NLP2018講演資料）/ Introduction of Deep Reinforcement Learning
Why Deep Learning Works II: the Renormalization Group
AAAS
GitHub - DeNA/SRCNNKit: CoreML and Keras implementation of Super-Resolution Convolutional Neural Network (SRCNN)
