Stable Diffusion を基礎から理解したい人向け論文攻略ガイド【無料記事】
GitHub - deeppomf/DeepLearningAnimePapers: A list of papers and other resources on deep learning with anime style images.
Dismiss Join GitHub today GitHub is home to over 50 million developers working together to host and review code, manage projects, and build software together. Sign up GitHub is where the world builds software Millions of developers and companies build, ship, and maintain their software on GitHub — the largest and most advanced development platform in the world.
府大生が趣味で世界一の認識精度を持つニューラルネットワークを開発してしまった論文を読んだ - Qiita
Deleted articles cannot be recovered. Draft of this article would be also deleted. Are you sure you want to delete this article? Deep Learning Advent Calendar 2016の20日目の記事です。 ConvNetの歴史とResNet亜種、ベストプラクティスに関連スライドがあります（追記） 背景 府大生が趣味で世界一の認識精度を持つニューラルネットワークを開発してしまったようです。 M2の学生が趣味でやっていたCIFAR10とCIFAR100の認識タスクで，現時点での世界最高性能の結果を出したそうだ…趣味でっていうのが…https://t.co/HKFLXTMbzx — ニーシェス (@lachesis1120) 2016年12月7日 府
【論文シリーズ】DNCー動的な記憶装置を搭載した人工知能 - Qiita
Deleted articles cannot be recovered. Draft of this article would be also deleted. Are you sure you want to delete this article? 原文のリンク Hybrid computing using a neural network with dynamic external memory (2016) 1. 要約と背景 DeepMind社（現Google子会社）は2016年10月27日に、全く新しいタイプの人工知能のフレームワークをNature論文に発表しました。その名も、DNC (Differential Neural Computer)といいます。 この人工知能の斬新な点は何と言っても外部記憶装置 (external memory)の存在です。これはヒトの海馬のような
awesome-deep-learning-papers/README.md at master · terryum/awesome-deep-learning-papers
Before this list, there exist other awesome deep learning lists, for example, Deep Vision and Awesome Recurrent Neural Networks. Also, after this list comes out, another awesome list for deep learning beginners, called Deep Learning Papers Reading Roadmap, has been created and loved by many deep learning researchers. Although the Roadmap List includes lots of important deep learning papers, it fee
深層強化学習論文リストを作り始めた - 学生時代に頑張ったことが何もない
前にDQNの再現の記事を書いてからほぼ1年が空いてしまいました．DQNの新しい論文が2月にNatureに載ったのは記憶に新しいですが，それから研究はさらに加速し，最近では自分の感覚としてはarxiv含めて平均すると1週間に1論文くらいのペースで深層強化学習の研究が発表されているのではないかと思います（ちゃんと計算してないので全然違ってたらすみません）． これだけ論文が増えるとまとめのようなものが欲しくなるので，自分で作ることにしました． https://github.com/muupan/deep-reinforcement-learning-papers まだだいぶ不完全ですし，論文リストをきちんとした形で作るのははじめてなのでいろいろと迷う部分があるのですが，これから少しずつ充実させていく予定です．
研究方法
■心構え（研究室配属） 研究室リテラシー (島田 伸敬) 増井研でこの先生きのこるには（慶応大学増井研究室・@shokai）…大学の研究室の生活についての解説． 伊藤研究室への配属志望学生の皆さんへ (お茶の水女子大学 伊藤研究室) アカデミックマナーの心得 (東京大学大学院 情報学環・学際情報学府) 研究が進まないとき，どうするかー「研究が何であるか」まだわかっていない言語研究者の卵のための助言ー (黒田 航) ■心構え（大学院進学・留学） 博士課程の誤解と真実 ー進学に向けて、両親を説得した資料をもとにー (小野田 淳人) （2015年版）博士進学が決まったあなたが今すぐに始めるべきこと (発声練習)…ここで書かれていることは，アカデミックポストに応募するだけに限らず，一般的な院生の就職活動にも非常に重要です． 企業での博士・海外での博士 〜IT業界を例にして〜 (お茶の水女子大学 伊
Improving neural networks by preventing co-adaptation of feature detectors
When a large feedforward neural network is trained on a small training set, it typically performs poorly on held-out test data. This "overfitting" is greatly reduced by randomly omitting half of the feature detectors on each training case. This prevents complex co-adaptations in which a feature detector is only helpful in the context of several other specific feature detectors. Instead, each neuro
Sequential Click Prediction for Sponsored Search with Recurrent Neural Networks
Click prediction is one of the fundamental problems in sponsored search. Most of existing studies took advantage of machine learning approaches to predict ad click for each event of ad view independently. However, as observed in the real-world sponsored search system, user's behaviors on ads yield high dependency on how the user behaved along with the past time, especially in terms of what queries
[PDF] Neural Word Embedding as Implicit Matrix Factorization (2014)
Neural Word Embedding as Implicit Matrix Factorization Omer Levy Department of Computer Science Bar-Ilan University omerlevy@gmail.com Yoav Goldberg Department of Computer Science Bar-Ilan University yoav.goldberg@gmail.com Abstract We analyze skip-gram with negative-sampling (SGNS), a word embedding method introduced by Mikolov et al., and show that it is implicitly factorizing a word-context ma
Learning to Execute
Learning to Execute Wojciech Zaremba WOJ.ZAREMBA@GMAIL.COM Google & New York University Ilya Sutskever ILYASU@GOOGLE.COM Google Abstract Recurrent Neural Networks (RNNs) with Long- Short Term Memory units (LSTM) are widely used because they are expressive and are easy to train. Our interest lies in empirically evalu- ating the expressiveness and the learnability of LSTMs by training them to evalua
Parallel training of DNNs with Natural Gradient and Parameter Averaging
We describe the neural-network training framework used in the Kaldi speech recognition toolkit, which is geared towards training DNNs with large amounts of training data using multiple GPU-equipped or multi-core machines. In order to be as hardware-agnostic as possible, we needed a way to use multiple machines without generating excessive network traffic. Our method is to average the neural networ
Deep Visual-Semantic Alignments for Generating Image Descriptions
Deep Visual-Semantic Alignments for Generating Image Descriptions We present a model that generates natural language descriptions of images and their regions. Our approach leverages datasets of images and their sentence descriptions to learn about the inter-modal correspondences between language and visual data. Our alignment model is based on a novel combination of Convolutional Neural Networks o
Skip-gram Language Modeling Using Sparse Non-negative Matrix Probability Estimation
We present a novel family of language model (LM) estimation techniques named Sparse Non-negative Matrix (SNM) estimation. A first set of experiments empirically evaluating it on the One Billion Word Benchmark shows that SNM $n$-gram LMs perform almost as well as the well-established Kneser-Ney (KN) models. When using skip-gram features the models are able to match the state-of-the-art recurrent ne
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
https://dl.acm.org/doi/10.1145/2827872
Subas CHHATKULI | AI Engineer | PhD | Engineering
GitHub - sbrugman/deep-learning-papers: Papers about deep learning ordered by task, date. Current state-of-the-art papers are labelled.
GitHub - terryum/awesome-deep-learning-papers: The most cited deep learning papers
https://cs.stanford.edu/people/karpathy/deepimagesent/devisagen.pdf
http://daggerfs.com/assets/pdf/nips12_rsvm.pdf