読者です 読者をやめる 読者になる 読者になる

Deep系の論文めも後半その1 (2016年夏頃までのもの対象)

論文・資料・スライド集 画像処理 深層学習 機械学習 書きかけ メモ

後半その1...?そもそも後半でまとめるのに無理があった。

前半:「過学習の防止・学習のアルゴリズム」、「理論」、「画像・動画からのキャプション生成」

paper.hatenadiary.jp

生成モデル

Deep Convolutional Generative Adversarial Networks

Generative Adversarial Nets

Goodfellow, Ian, et al. "Generative adversarial nets." Advances in Neural Information Processing Systems. 2014.

papers.nips.cc

www.slideshare.net

Unsupervised representation learning with deep convolutional generative adversarial networks

Radford, Alec, Luke Metz, and Soumith Chintala. "Unsupervised representation learning with deep convolutional generative adversarial networks." arXiv preprint arXiv:1511.06434 (2015).

www.slideshare.net

Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks

Denton, Emily L., Soumith Chintala, and Rob Fergus. "Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks." Advances in neural information processing systems. 2015.

www.slideshare.net

Energy-based Generative Adversarial Network

Zhao, Junbo, Michael Mathieu, and Yann LeCun. "Energy-based Generative Adversarial Network." arXiv preprint arXiv:1609.03126 (2016).

Pixel recurrent neural networks

pdf: [1601.06759] Pixel Recurrent Neural Networks

van den Oord, Aaron, Nal Kalchbrenner, and Koray Kavukcuoglu. "Pixel Recurrent Neural Networks." arXiv preprint arXiv:1601.06759 (2016).

www.slideshare.net

WaveNet: A Generative Model for Raw Audio

deepmind.com

www.slideshare.net

その他資料

www.slideshare.net

モデルの圧縮・パラメータの削減

SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 1MB model size

arxiv: [1602.07360] SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and &lt;0.5MB model size

Iandola, Forrest N., et al. "SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 1MB model size." arXiv preprint arXiv:1602.07360 (2016).

qiita.com

www.slideshare.net

Eie: Efficient inference engine on compressed deep neural network

arxiv: [1602.01528] EIE: Efficient Inference Engine on Compressed Deep Neural Network

こちらにてスタンフォード大学の資料を直接閲覧できます。

f:id:misos:20161104103306p:plain

その他

Learning to Compose Neural Networks for Question Answering

arxiv: [1601.01705] Learning to Compose Neural Networks for Question Answering

Andreas, Jacob, et al. "Learning to compose neural networks for question answering." arXiv preprint arXiv:1601.01705 (2016).

speakerdeck.com

Adaptive Computation Time for Recurrent Neural Networks

arxiv: [1603.08983] Adaptive Computation Time for Recurrent Neural Networks

Graves, Alex. "Adaptive Computation Time for Recurrent Neural Networks." arXiv preprint arXiv:1603.08983 (2016).

distill.pub