47. GAN 敵対的⽣生成モデル
z
x = G(z)
x
次の⼿手順でxを⽣生成する
(1) z 〜~ U(0, I)でサンプリングする
(2) x = G(z)を計算する
最後にサンプリング
がないことに注意p(z)がGaussianでなく
⼀一様分布Uを使うのも特徴
⾼高次元の⼀一様分布の場合
隅が離離れた表現を扱える
48. GAN 敵対的⽣生成モデルの学習
l 偽物かを判定するD(x)を⽤用意
̶— 本物なら1, 偽物なら0を返す
l Dは上式を最⼤大化するように学習し
Gは最⼩小化するように学習する
̶— この学習はうまく進めば
∫p(z)G(z)dz=P(x), D(x)=1/2という
均衡解にたどり着ける
z
x'
x = G(z)
{1(本物), 0(偽物)}
y = D(x)
x
64. 参考⽂文献
l [Lin+ 16] “Why does deep and cheap learning work so well?”, H. W. Lin, M.
Tegmark
l [Vinnikov+ 14] “K-means Recovers ICA Filters when Independent
Components are Sparse”, ICML 2014, A. Vinnikov, S. S.-Shwartz
l [Kingma+ 13] ”Auto-encoding Variational Bayes”, D. P. Kingma, M. Welling
l [Kingma+ 14] “Semi-supervised Learning with Deep Generative Models”, D.
P. Kingma, D. J. Rezende, S. Mohamed, M. Welling
l [Burda+ 15] “Importance weighted autoencoders”, Y. Burda, R. Grosse, R.
Salakhutdinov
l [Maaloe+ 16] ”Auxiliary Deep Generative Models”, L. Maaloe, c. K.
Sonderby, S. K. Sonderby, O. Winther
l [Goodfellow+ 14] “Gerative Adversarial Networks”, I. J. Goodfellow and et.
al.
65. l [Salimans+ 16] ”Improved Techniques for Training GANs”, T. Salimans, I.
Goodfellow, W. Zaremba, V. Cheung, A. Radford, X. Chen
l [Oord+ 16a] “Pixcel Reucurrent Neural Network”, A. Oord. et al.
l [Oord+ 16b] “Conditional Image Generation with PixelCNN Decoders”, A.
Oord et al.
l [Oord+ 16c] “WaveNet: A Generative Model for Raw Audito”, A. Oord et al.
l [Kim+ 16] “Deep Directed Generative Models with Energy-based Probability
estimation”, T. Kim, Y. Bengio
l [Li+ 15] “Generative Moment Matching Network”, Y. Li, K. Swersky, R.
Zemel
l [Dahl+ 14] “Multi-task Neural Networks for QSAR Predictions”, G. E. Dahl, N.
Jaitly, R. alakhutdinov
l [Lee+ 16] “DeepTarget: End-to-end Learning Framework for microRNA
Target Prediction using Deep Recurrent Neural Networks”, B. Leett, J. Baek,
S. Park, S. Yoon