ベイズ最適化によるハイパーパラメータ探索についてざっくりと解説しました。
今回紹介する内容の元となった論文
Bergstra, James, et al. "Algorithms for hyper-parameter optimization." 25th annual conference on neural information processing systems (NIPS 2011). Vol. 24. Neural Information Processing Systems Foundation, 2011.
https://hal.inria.fr/hal-00642998/
NIPS KANSAI Reading Group #7: 逆強化学習の行動解析への応用Eiji Uchibe
Can AI predict animal movements? Filling gaps in animal trajectories using inverse reinforcement learning, Ecosphere,
Modeling sensory-motor decisions in natural behavior, PLoS Comp. Biol.
NIPS KANSAI Reading Group #7: 逆強化学習の行動解析への応用Eiji Uchibe
Can AI predict animal movements? Filling gaps in animal trajectories using inverse reinforcement learning, Ecosphere,
Modeling sensory-motor decisions in natural behavior, PLoS Comp. Biol.
論文紹介:Dueling network architectures for deep reinforcement learningKazuki Adachi
Wang, Ziyu, et al. "Dueling network architectures for deep reinforcement learning." Proceedings of The 33rd International Conference on Machine Learning, PMLR 48:1995-2003, 2016.
[Paper Reading] Learning Distributed Representations for Structured Output Pr...Yusuke Iwasawa
1) The document proposes a new method called DISTRO that uses distributed representations for structured output prediction tasks.
2) DISTRO represents labels as dense real-valued vectors rather than one-hot vectors, and defines compositionality of labels using tensor products of label vectors.
3) Experiments on document classification and part-of-speech tagging show that DISTRO outperforms baselines by learning label vectors that capture similarities between labels.
2. 書誌情報
• Nature (Deep Mind3本目)
• 2016/10/12 published
• 引用21
• 著者 (20人,すべてDeepMind)
Alex Graves, Greg Wayne, Malcolm Reynolds, Tim Harley, Ivo Danihelka,
Agnieszka Grabska-Barwińska, Sergio Gómez Colmenarejo, Edward Grefenstette,
Tiago Ramalho, John Agapiou, Adrià Puigdomènech Badia, Karl Moritz Hermann,
Yori Zwols, Georg Ostrovski, Adam Cain, Helen King, Christopher Summerfield,
Phil Blunsom, Koray Kavukcuoglu & Demis Hassabis
37. Controllerが出力するものまとめ
• 読み込み関連
– R個の読込キーベクトル: kri
t
– R個の読込強さ: βri
t
– R個の読み込みモード: πi
t
• 書き込み関連
– 1個の書き込みキーベクトル: kr
t
– 1個の書き強さ: βr
t
– 消去ベクトル: et
– 書き込みベクトル: vt
– R個のfree gates: fi
t
– allocation gate: ga
t
これに最終的な出力yを加えたベクトルを1つのNNで出力
NNはLSTMで表現 (実際はなんでも良い)