Bookmarks

for artificial intelligence, computer science and linguistics

2015-05-01

強化学習をベイズで理解する

https://www.sat.t.u-tokyo.ac.jp/~mak/20140319-makino.pdf
Labels:  2014, ベイズ, 強化学習, 牧野貴樹
Newer Post Older Post Home

Links

  • Bookmarks » Corpus & Data

Search This Blog

Popular Posts

  • A deviation of CURAND: standard pseudorandom number generator in CUDA for GPGPU
  • Java8のHotSpotVMからPermanent領域が消えた理由とその影響 | ギークを目指して
  • 共変量シフト適応 - 東京大学 杉山・佐藤研究室
  • plotly.js | JavaScript Graphing Library
  • 福島邦彦: Deep CNN ネオコグニトロンの学習
  • unnonouno: AdaGradが12倍速くなる魔法
  • DotNetZip/CRC32.cs at master · HalfVoxel/DotNetZip · GitHub
  • CIFAR-10でstate of the artのスコアが出せる、インターネットに落ちている中で最強のコード - デー
  • Performance Benefits of Half Precision Floats | Intel® Software

Labels

  • __proto__ (1)
  • 2006 (1)
  • 2007 (1)
  • 2010 (1)
  • 2013 (2)
  • 2014 (4)
  • 2015 (4)
  • 2016 (5)
  • AdaGrad (1)
  • Adam (1)
  • AGI (1)
  • AI (3)
  • AiS (1)
  • Alexander M. Rush (1)
  • algorithms (7)
  • allocator (2)
  • Andrej Karpathy (5)
  • Arild Nøkland (1)
  • artificial intelligence (2)
  • Attentive Reader (1)
  • AVX (1)
  • B-tree (1)
  • batch normalization (1)
  • benchmarks (1)
  • Benjamin Schrauwen (2)
  • Bianca Zadrozny (1)
  • binary16 (2)
  • Brotli (2)
  • C (4)
  • C# (1)
  • C´ıcero Nogueira dos Santos (1)
  • C++ (11)
  • C++11 (1)
  • cedar (1)
  • CELP (1)
  • Chainer (2)
  • Chao Dong (2)
  • Chart (1)
  • Christopher D. Manning (1)
  • Christopher Manning (1)
  • CIFAR-10 (3)
  • CIFAR-100 (1)
  • CNN (3)
  • compression (4)
  • computer vision (9)
  • convolutional network (11)
  • convolutional neural network (5)
  • corpus (5)
  • covariate shift (3)
  • CRC32 (1)
  • CRIC (1)
  • CUDA (5)
  • cuda-convnet2 (1)
  • cuDNN (2)
  • cuRAND (1)
  • CVPR (2)
  • database (2)
  • David Sontag (1)
  • David Verstraeten (1)
  • deep learning (32)
  • DeepMind (2)
  • deflate (1)
  • Denny Britz (1)
  • dictionary (2)
  • Diederik Kingma (1)
  • dimensionality reduction (1)
  • Djamal Belazzougui (1)
  • DNN (1)
  • Dong Yu (1)
  • double array trie (1)
  • dropout (1)
  • echo state network (4)
  • Edward Grefenstette (1)
  • Elad Hazan (1)
  • Eve optimizer (1)
  • file format (2)
  • finite impulse response (2)
  • finite state transducer (1)
  • float (1)
  • format:mp3 (1)
  • FP16 (4)
  • framework (3)
  • FST (1)
  • GAN (1)
  • Generative Adversarial Networks (1)
  • Geoffrey Hinton (1)
  • GeoLite (2)
  • GloVe (1)
  • Google (3)
  • Graham Neubig (2)
  • hash (1)
  • Herbert Jaeger (1)
  • Hidetoshi Nishimori (1)
  • HIP Estimator (1)
  • Hiroaki Hayashi (1)
  • Hiroyuki Tokunaga (1)
  • Hoa Trang Dang (1)
  • HotSpotVM (1)
  • HPYLM (1)
  • HTML (1)
  • HTML5 (1)
  • Huffman (1)
  • hwloc (1)
  • HyperLogLog (3)
  • IBM (6)
  • id:ultraist (1)
  • idsia.ch (1)
  • IEEE 754 (2)
  • illustration (1)
  • ILMerge (1)
  • Ilya Sutskever (2)
  • Impatient Reader (1)
  • information retrieval (1)
  • Intel (1)
  • Intel intrinsic instructions (1)
  • IP (2)
  • IRNN (1)
  • Jan Van Campenhout (1)
  • Japanese language (7)
  • Java (4)
  • Java8 (1)
  • JavaScript (7)
  • Jayanth Koushik (1)
  • Jeffrey Pennington (1)
  • Jimmy Ba (1)
  • JSON (2)
  • JSONL (1)
  • kanji (2)
  • Karl Moritz Hermann (2)
  • Karolina Owczarzak (1)
  • Kfir Y. Levy (1)
  • Klaus Greff (1)
  • Kunihiko Fukushima (1)
  • Ladder Network (1)
  • language model (2)
  • Lasse Espeholt (1)
  • Laurens van der Maaten (1)
  • LDJSON (1)
  • Lei Yu (1)
  • Li Deng (1)
  • library (2)
  • license:Apache License 2.0 (1)
  • license:MIT (1)
  • Lin Xiao (1)
  • LINE (1)
  • liquid state machine (2)
  • LiquidFun (1)
  • livedoor ニュース (1)
  • low-discrepancy sequence (1)
  • LSTM (6)
  • machie learning (1)
  • Marek Rei (1)
  • Marvin (1)
  • Matthieu Courbariaux (1)
  • maxDNN (1)
  • memory (2)
  • Michael Nielsen (1)
  • Michiel Hermans (1)
  • Microsoft (2)
  • Microsoft Research (2)
  • MinHash (1)
  • minimal acyclic subsequential transducer (1)
  • MLlib (1)
  • MNIST (1)
  • Mustafa Suleyman (1)
  • Nayuki (1)
  • ndjson (2)
  • neocognitron (1)
  • neural network (27)
  • neural processing units (1)
  • NLP (21)
  • NLU (1)
  • NTCIR STC (1)
  • object detection (1)
  • Odd Sketch (1)
  • ontology (1)
  • opensource (6)
  • Oriol Vinyals (1)
  • Oxford (1)
  • paper (3)
  • patent (2)
  • Patrick Konsor (1)
  • Phil Blunsom (2)
  • Pierre Sermanet (1)
  • POS (1)
  • PPM (2)
  • preferred.jp (2)
  • Princeton Vision Group (1)
  • prototype (1)
  • PST (1)
  • Python (2)
  • Qualcomm (1)
  • quantum annealing (1)
  • quasi-random numbers (1)
  • quasi-random sequence (1)
  • Rakuten MA (1)
  • random numbers (3)
  • RDA (1)
  • recurrent network (4)
  • recurrent neural network (2)
  • Regularized Dual Averaging (1)
  • ReLU (3)
  • reservoir computing (5)
  • Richard Socher (2)
  • Robert Dionne (1)
  • Roland Memisevic (1)
  • Rondhuit (1)
  • rsqrt (1)
  • rti7743 (1)
  • Ryan Dahl (1)
  • search (1)
  • SENNA (1)
  • seq2seq (1)
  • Shai Shalev-Shwartz (1)
  • ShiLiang Zhang (1)
  • Shunji Mitsuyoshi (4)
  • Simon Puglisi (1)
  • Skip-Thought (1)
  • softmax (1)
  • Spark (1)
  • sparsehash (3)
  • speech recognition (1)
  • splay-tree (3)
  • SRCNN (2)
  • SSE (1)
  • Stanford university (6)
  • subword (1)
  • t-SNE (1)
  • TAC (1)
  • TD学習 (1)
  • TensorFlow (2)
  • Text Analysis Conference (1)
  • textbook (1)
  • tf-idf (1)
  • Theano (1)
  • thread (1)
  • Tim Waegeman (1)
  • tokenizer (1)
  • Tomas Kocisky (1)
  • Tomas Mikolov (1)
  • Torch7 (1)
  • trie (1)
  • TrueNorth (5)
  • tutorials (1)
  • Twitter (1)
  • Visual C# (1)
  • visual recognition (1)
  • visual similarity (1)
  • Visual Studio (1)
  • Visual Studio 2017 (1)
  • WARC (1)
  • web crawler (1)
  • Webサービス (1)
  • wikipedia (4)
  • Will Kay (1)
  • Wojciech Zaremba (1)
  • word representation (1)
  • word2vec (2)
  • XORWOW (1)
  • Yacine Jernite (1)
  • Yann LeCun (1)
  • Yisong Yue (1)
  • Yoon Kim (1)
  • Yoshua Bengio (2)
  • Yuya Unno (1)
  • Zhouhan Lin (1)
  • zlib (1)
  • Zopfli (2)
  • インタビュー (1)
  • シモセラ エドガー (1)
  • データ圧縮 (4)
  • テンソル (1)
  • トピックモデル (1)
  • ニューロモーフィック (1)
  • ひろたかなん (1)
  • ベイジアンHMM (1)
  • ベイズ (1)
  • ベクトル (1)
  • りんな (2)
  • 三上章允 (1)
  • 乱数 (3)
  • 人工無能 (2)
  • 今井むつみ (1)
  • 企業 (1)
  • 伊藤真 (1)
  • 光吉俊二 (4)
  • 公益社団法人著作権情報センター (1)
  • 共変量シフト (3)
  • 最適化 (1)
  • 分散共分散行列 (1)
  • 前頭前野 (1)
  • 北海道大学 (1)
  • 合原一幸 (1)
  • 品詞 (1)
  • 図書館学 (1)
  • 大脳基底核 (3)
  • 大脳皮質 (1)
  • 対話システム (2)
  • 小嶋祥三 (1)
  • 山口高平 (1)
  • 岡崎直観 (1)
  • 岡谷貴之 (1)
  • 岡野原大輔 (1)
  • 川人光男 (1)
  • 強化学習 (3)
  • 形態素解析 (1)
  • 得居誠也 (1)
  • 心理学 (1)
  • 情報検索 (1)
  • 感性理解 (1)
  • 感情 (1)
  • 感情分析 (1)
  • 感情地図 (1)
  • 感情理解 (2)
  • 感情認識 (3)
  • 持橋大地 (5)
  • 携帯電話 (1)
  • 放送大学 (1)
  • 数学 (3)
  • 文法圧縮 (1)
  • 文法障害 (1)
  • 日本神経回路学会 (1)
  • 日本語音声コーパス (1)
  • 有限インパルス応答 (2)
  • 杉山将 (2)
  • 東京大学 (1)
  • 東京女子医科大学 (1)
  • 東京都医学総合研究所 (1)
  • 東北大学 (1)
  • 松井勇佑 (2)
  • 松田耕史 (1)
  • 機械学習 (1)
  • 次元削減 (1)
  • 次元圧縮 (1)
  • 海野裕也 (2)
  • 準乱数 (1)
  • 漢字 (1)
  • 無限HMM (1)
  • 牧野貴樹 (1)
  • 物体検出 (1)
  • 物体認識 (1)
  • 特許 (1)
  • 玉川奨 (1)
  • 甘利俊一 (1)
  • 田部井靖生 (1)
  • 画像認識 (1)
  • 発達心理学 (1)
  • 相関行列 (1)
  • 神経回路 (1)
  • 神経科学 (7)
  • 福島邦彦 (1)
  • 秋葉拓哉 (1)
  • 科学技術振興機構 (1)
  • 統計数理 (1)
  • 線条体 (1)
  • 脳 (8)
  • 自動要約 (1)
  • 自然言語処理 (5)
  • 著作権 (1)
  • 行列 (1)
  • 西森秀稔 (1)
  • 言語 (1)
  • 言語モデル (2)
  • 言語獲得 (1)
  • 認知心理学 (1)
  • 認知神経科学 (2)
  • 辞書 (2)
  • 量子アニーリング (1)
  • 銅谷賢治 (2)
  • 長尾真 (1)
  • 非再帰形ディジタルフィルタ (2)
  • 黒橋禎夫 (1)
  • 黒須正明 (1)
  • 齋藤真樹 (2)

Blog Archive

  • ►  2017 (9)
    • ►  August (1)
    • ►  May (1)
    • ►  April (1)
    • ►  March (6)
  • ►  2016 (29)
    • ►  November (4)
    • ►  October (3)
    • ►  July (2)
    • ►  June (3)
    • ►  May (1)
    • ►  March (3)
    • ►  February (4)
    • ►  January (9)
  • ▼  2015 (86)
    • ►  December (4)
    • ►  November (7)
    • ►  October (8)
    • ►  September (7)
    • ►  August (7)
    • ►  July (8)
    • ►  June (7)
    • ▼  May (9)
      • 場所参照表現タグ付きコーパス Ver 0.1 (2015/05/25)
      • Computing numeric representations of words in a hi...
      • ConvNetJS MNIST demo
      • The Unreasonable Effectiveness of Recurrent Neural...
      • Andrej Karpathy Academic Website
      • karpathy/convnetjs · GitHub
      • ConvNetJS: Deep Learning in your browser
      • 分散共分散行列と相関行列
      • 強化学習をベイズで理解する
    • ►  April (14)
    • ►  March (12)
    • ►  January (3)
  • ►  2014 (55)
    • ►  November (4)
    • ►  October (2)
    • ►  August (25)
    • ►  July (24)
Bookmarked by bookmarks2022. Simple theme. Powered by Blogger.