雷鋒網(wǎng)消息，谷歌大腦團隊的 Ian Goodfellow 今日在研究院官網(wǎng)上撰文，總結(jié)了谷歌在 ICLR 2017 上所做的學(xué)術(shù)貢獻。雷鋒網(wǎng)編譯全文如下，未經(jīng)許可不得轉(zhuǎn)載。

本周，第五屆國際學(xué)習(xí)表征會議（ICLR 2017）在法國土倫召開，這是一個關(guān)注機器學(xué)習(xí)領(lǐng)域如何從數(shù)據(jù)中習(xí)得具有意義及有用表征的會議。ICLR 包括 conference track 及 workshop track 兩個項目，邀請了獲得 oral 及 poster 的研究者們進行分享，涵蓋深度學(xué)習(xí)、度量學(xué)習(xí)、核學(xué)習(xí)、組合模型、非線性結(jié)構(gòu)化預(yù)測，及非凸優(yōu)化問題。

站在神經(jīng)網(wǎng)絡(luò)及深度學(xué)習(xí)領(lǐng)域浪潮之巔，谷歌關(guān)注理論與實踐，并致力于開發(fā)理解與總結(jié)的學(xué)習(xí)方法。作為 ICLR 2017 的白金贊助商，谷歌有超過 50 名研究者出席本次會議（大部分為谷歌大腦團隊及谷歌歐洲研究分部的成員），通過在現(xiàn)場展示論文及海報的方式，為建設(shè)一個更完善的學(xué)術(shù)研究交流平臺做出了貢獻，也是一個互相學(xué)習(xí)的過程。此外，谷歌的研究者也是 workshops 及組委會構(gòu)建的中堅力量。

如果你來到 ICLR 2017，我們希望你能在我們的展臺前駐足，并與我們的研究者進行交流，探討如何為數(shù)十億人解決有趣的問題。

以下為谷歌在 ICLR 2017 展示的論文內(nèi)容（其中的谷歌研究者已經(jīng)加粗表示）

區(qū)域主席

George Dahl, Slav Petrov, Vikas Sindhwani

程序主席（雷鋒網(wǎng)此前已經(jīng)做過相關(guān)介紹）

Hugo Larochelle, Tara Sainath

受邀演講論文

• Understanding Deep Learning Requires Rethinking Generalization (Best Paper Award)

  Chiyuan Zhang*, Samy Bengio, Moritz Hardt, Benjamin Recht*, Oriol Vinyals

• Semi-Supervised Knowledge Transfer for Deep Learning from Private Training Data (Best Paper Award)

  Nicolas Papernot*, Martín Abadi, úlfar Erlingsson, Ian Goodfellow, Kunal Talwar

• Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic

  Shixiang (Shane) Gu*, Timothy Lillicrap, Zoubin Ghahramani, Richard E. Turner, Sergey Levine

• Neural Architecture Search with Reinforcement Learning

  Barret Zoph, Quoc Le

Poster 論文

• Adversarial Machine Learning at Scale

  Alexey Kurakin, Ian J. Goodfellow?, Samy Bengio

• Capacity and Trainability in Recurrent Neural Networks

  Jasmine Collins, Jascha Sohl-Dickstein, David Sussillo

• Improving Policy Gradient by Exploring Under-Appreciated Rewards

  Ofir Nachum, Mohammad Norouzi, Dale Schuurmans

• Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer

  Noam Shazeer, Azalia Mirhoseini, Krzysztof Maziarz, Andy Davis, Quoc Le, Geoffrey Hinton, Jeff Dean

• Unrolled Generative Adversarial Networks

  Luke Metz, Ben Poole*, David Pfau, Jascha Sohl-Dickstein

• Categorical Reparameterization with Gumbel-Softmax

  Eric Jang, Shixiang (Shane) Gu*, Ben Poole*

• Decomposing Motion and Content for Natural Video Sequence Prediction

  Ruben Villegas, Jimei Yang, Seunghoon Hong, Xunyu Lin, Honglak Lee

• Density Estimation Using Real NVP

  Laurent Dinh*, Jascha Sohl-Dickstein, Samy Bengio

• Latent Sequence Decompositions

  William Chan*, Yu Zhang*, Quoc Le, Navdeep Jaitly*

• Learning a Natural Language Interface with Neural Programmer

  Arvind Neelakantan*, Quoc V. Le, Martín Abadi, Andrew McCallum*, Dario Amodei*

• Deep Information Propagation

  Samuel Schoenholz, Justin Gilmer, Surya Ganguli, Jascha Sohl-Dickstein

• Identity Matters in Deep Learning

  Moritz Hardt, Tengyu Ma

• A Learned Representation For Artistic Style

  Vincent Dumoulin*, Jonathon Shlens, Manjunath Kudlur

• Adversarial Training Methods for Semi-Supervised Text Classification

  Takeru Miyato, Andrew M. Dai, Ian Goodfellow?

• HyperNetworks

  David Ha, Andrew Dai, Quoc V. Le

• Learning to Remember Rare Events

  Lukasz Kaiser, Ofir Nachum, Aurko Roy*, Samy Bengio

Workshop Track

• Particle Value Functions

  Chris J. Maddison, Dieterich Lawson, George Tucker, Nicolas Heess, Arnaud Doucet, Andriy Mnih, Yee Whye Teh

• Neural Combinatorial Optimization with Reinforcement Learning

  Irwan Bello, Hieu Pham, Quoc V. Le, Mohammad Norouzi, Samy Bengio

• Short and Deep: Sketching and Neural Networks

  Amit Daniely, Nevena Lazic, Yoram Singer, Kunal Talwar

• Explaining the Learning Dynamics of Direct Feedback Alignment

  Justin Gilmer, Colin Raffel, Samuel S. Schoenholz, Maithra Raghu, Jascha Sohl-Dickstein

• Training a Subsampling Mechanism in Expectation

  Colin Raffel, Dieterich Lawson

• Tuning Recurrent Neural Networks with Reinforcement Learning

  Natasha Jaques*, Shixiang (Shane) Gu*, Richard E. Turner, Douglas Eck

• REBAR: Low-Variance, Unbiased Gradient Estimates for Discrete Latent Variable Models

  George Tucker, Andriy Mnih, Chris J. Maddison, Jascha Sohl-Dickstein

• Adversarial Examples in the Physical World

  Alexey Kurakin, Ian Goodfellow?, Samy Bengio

• Regularizing Neural Networks by Penalizing Confident Output Distributions

  Gabriel Pereyra, George Tucker, Jan Chorowski, Lukasz Kaiser, Geoffrey Hinton

• Unsupervised Perceptual Rewards for Imitation Learning

  Pierre Sermanet, Kelvin Xu, Sergey Levine

• Changing Model Behavior at Test-time Using Reinforcement Learning

  Augustus Odena, Dieterich Lawson, Christopher Olah

* 工作內(nèi)容在谷歌就職時完成

? 工作內(nèi)容在 OpenAI 任職時完成

詳細(xì)信息可訪問 research.googleblog 了解，雷鋒網(wǎng)編譯。

雷峰網(wǎng)版權(quán)文章，未經(jīng)授權(quán)禁止轉(zhuǎn)載。詳情見轉(zhuǎn)載須知。