【一文打盡 ICLR 2018】9大演講,DeepMind、谷歌最新乾貨搶鮮看

原標題：【一文打盡 ICLR 2018】9大演講，DeepMind、谷歌最新乾貨搶鮮看

來源：iclr、Google/DeepMind blog

【新智元導讀】ICLR 2018即將開幕，谷歌、DeepMind等大廠這幾天陸續公布了今年的論文，全是乾貨。連同3篇最佳論文和9個邀請演講一起，新智元帶來本屆ICLR亮點的最全整理。

ICLR 2018即將在明天（當地時間4月30日）在溫哥華開幕，谷歌、DeepMind等大廠這幾天陸續公布了今年的論文，全是乾貨。連同3篇最佳論文一起，新智元帶來本屆ICLR亮點的最全整理。

ICLR 2018為期4天，5月3日結束。與往年一樣，本次大會每天分上午下午兩場。每場形式基本一樣，先是邀請演講（invited talk），然後是討論，也就是被選為能夠進行口頭髮表（Oral）的論文、茶歇、海報展示（poster）。

邀請演講列表：

9個邀請演講主題：

• Erik Brynjolfsson：機器學習能做什麼？ 勞動力影響
• Bernhard Schoelkopf:學習因果機制
• Suchi Saria：通過機器學習將醫療個性化
• Kristen Grauman：未標記的視頻的視覺學習與環視策略
• Koray Kavukcuoglu：從生成模型到生成agents
• Blake Richards：深度學習與Neocortical Microcircuits
• Daphne Koller：與Daphne Koller的爐邊聊天
• Joelle Pineau：深度強化學習中的可重複性，可重用性和魯棒性
• Christopher D Manning：一個可以推理的神經網絡模型

大會主席

Yoshua Bengio，蒙特婁大學

Yann LeCun，紐約大學&Facebook

高級程序主席

Tara Sainath，Google

程序主席

Iain Murray，愛丁堡大學

Marc'Aurelio Ranzato，Facebook

Oriol Vinyals，Google DeepMind

指導委員會

Aaron Courville，蒙特婁大學

Hugo Larochelle，Google

領域主席（Area Chairs）

最佳評審人：

Amir-massoud Farahmand，Andrew Owens，David Kale，George Philipp，Julien Cornebise，Michiel van de Panne，Tom Schaul，Yisong Yue

ICLR素有深度學習頂會「無冕之王」之稱。Dataviz網站之前統計了今年的ICLR數據，有以下幾個有意思的地方：

• 來自加州大學伯克利分校的Sergey Levine被接收論文數量最多；
• 大神Bengio提交論文數量最多；
• 谷歌的接收和提交論文數量都屬機構第一；
• 英偉達的接收率排名第一；
• 提交和被接收論文數量，英國都獨佔鰲頭；
• 中國是繼英國之後，提交論文數量最多的國家。

接收論文數量最多的機構：谷歌第一、伯克利第二、斯坦福第三

如果一篇論文的所有作者都來自同一個機構，該機構被算作寫了一篇論文。如果三位作者中只有一位來自該機構，則認為該機構寫了三分之一篇論文。

谷歌以3.33篇oral、42.78篇poster和0.56的接收率稱霸榜首；伯克利名列第二，oral為2.56篇、poster為10.48篇，接收率為0.46；斯坦福排名第三，oral為1篇，poster為9.4篇，接收率為0.36。

前10名餘下機構分別是：CMU、Facebook、微軟、牛津大學、IBM、多倫多大學、ETH。

以下帶來ICLR 2018的最佳論文的介紹，以及DeepMind和谷歌的論文概況。

論文下載地址：

https://deepmind.com/blog/deepmind-papers-iclr-2018/

https://research.googleblog.com/2018/04/google-at-iclr-2018.html

最佳論文3篇：Adam新算法，球形CNN，learning to learn框架等受關注

最佳論文1：

On the Convergence of Adam and Beyond

關於 Adam 算法收斂性及其改進方法的討論

作者：Sashank J. Reddi, Satyen Kale, Sanjiv Kumar

本研究的貢獻：

1. 通過一個簡單的凸優化問題闡述了TMSprop和Adam中使用的指數移動平均是如何導致不收斂的。而且文中的分析可以擴展到其他的指數移動平均打的方法上如Adadelta和NAdam。
2. 為了保證算法的收斂，文中使用歷史梯度的「長時記憶」。並指出了在以往論文Kingma&Ba(2015）中關於Adam收斂性證明過程中存在的問題。為了解決這個問題，文中提出了Adam的變體算法，算法在使用歷史梯度的「長時記憶」的情況下，並沒有增加算法的時間複雜度與空間複雜度。此外，文中還基於Kingma&Ba(2015)給出了Adam算法收斂性的分析。
3. 提供了Adam算法變體的實驗證明，結果表明，在某些常用的機器學習問題中，這個變體的表現算法相似或優於原始算法。

最佳論文2：

球形卷積神經網絡（Spherical CNNs）

卷積神經網絡（CNN）可以很好的處理二維平面圖像的問題。然而，對球面圖像進行處理需求日益增加。例如，對無人機、機器人、自動駕駛汽車、分子回歸問題、全球天氣和氣候模型的全方位視覺處理問題。將球形信號的平面投影作為卷積神經網絡的輸入的這種天真做法是註定要失敗的，如下圖1所示，而這種投影引起的空間扭曲會導致CNN無法共享權重。

圖1

這篇論文中介紹了如何構建球形CNN的模塊，提出了利用廣義傅立葉變換（FFT）進行快速群卷積（互相關）的操作。通過傅立葉變換來實現球形CNN的示意圖如下所示：

最佳論文3：

Continuous Adaptation via Meta-learning in Nonstationary and Competitive Environments

在非固定和競爭環境中通過元學習進行持續性適應

在非平穩環境中不斷學習和適應有限經驗的能力是計算機通往真正的人工智慧的重要裡程碑。此文提出了「learning to learn」框架的持續性適應問題。通過設計一種基於梯度的元學習算法來對動態變化和對抗性場景的進行適應。此外，文中還設計了一種基於多智能體（multi-agent）的競爭環境：RoboSumo，並定義了適應性迭代遊戲，用於從不同方面測試系統的持續適應性能。實驗證明，元學習比在few-shot狀態下的反應基線具有更強的適應能力，且適應於進行multi-agent學習和競爭。

實驗中使用了三種模型作為智能體（agent），如圖1（a） 所示。它們在解剖學上存在差異：腿的數量，位置，以及對大腿和膝關節的限制。下圖表示非平穩運動環境。應用於紅顏色的腿的扭矩是由一個動態變化的因素決定的。(c)用於表示 RoboSumo競爭環境。

DeepMind ICLR 2018論文集

最大後驗策略優化

Maximum a posteriori policy optimisation

作者：Abbas Abdolmaleki, Jost Tobias Springenberg, Nicolas Heess, Yuval Tassa, Remi Munos

高效架構搜索的層次化表示

Hierarchical representations for efficient architecture search

作者：Hanxiao Liu (CMU), Karen Simonyan, Oriol Vinyals, Chrisantha Fernando, Koray Kavukcuoglu

一個可遷移機器人技能的嵌入空間學習

Learning an embedding space for transferable robot skills

作者：Karol Hausman, Jost Tobias Springenberg, Ziyu Wang, Nicolas Heess, Martin Riedmiller

有意識模型的學習

Learning awareness models

作者：Brandon Amos, Laurent Dinh, Serkan Cabi, Thomas Rothörl, Sergio Gómez Colmenarejo, Alistair M Muldal, Tom Erez, Yuval Tassa, Nando de Freitas, Misha Denil

重複神經網絡的曲率近似法

Kronecker-factored curvature approximations for recurrent neural networks

作者：James Martens, Jimmy Ba (Vector Institute), Matthew Johnson (Google)

分布式分布確定性策略梯度

Distributed distributional deterministic policy gradients

作者：Gabriel Barth-maron, Matthew Hoffman, David Budden, Will Dabney, Daniel Horgan, Dhruva Tirumala Bukkapatnam, Alistair M Muldal, Nicolas Heess, Timothy Lillicrap

Kanerva機器：一個生成的分布式內存

The Kanerva Machine: A generative distributed memory

作者：Authors: Yan Wu, Greg Wayne, Alex Graves, Timothy Lillicrap

基於內存的參數適應

Memory-based parameter adaptation

作者：Pablo Sprechmann, Siddhant Jayakumar, Jack Rae, Alexander Pritzel, Adria P Badia · Benigno Uria, Oriol Vinyals, Demis Hassabis, Razvan Pascanu, Charles Blundell

SCAN：學習層次組合的視覺概念

SCAN: Learning hierarchical compositional visual concepts

作者：Irina Higgins, Nicolas Sonnerat, Loic Matthey, Arka Pal, Christopher P Burgess, Matko Bos ̌njak, Murray Shanahan, Matthew Botvinick, Alexander Lerchner

從帶有符號和像素輸入的引用遊戲中出現語言通信

Emergence of linguistic communication from referential games with symbolic and pixel input

作者：Angeliki Lazaridou, Karl M Hermann, Karl Tuyls, Stephen Clark

通向平衡之路：GAN不需要在每一步中減少散度

Many paths to equilibrium: GANs do not need to decrease a divergence at every step

作者：William Fedus (Université de Montréal), Mihaela Rosca, Balaji Lakshminarayanan, Andrew Dai (Google), Shakir Mohamed, Ian Goodfellow (Google Brain)

神經網絡能理解邏輯推理嗎？

Can neural networks understand logical entailment?

作者：Richard Evans, David Saxton, David Amos, Pushmeet Kohli, Edward Grefenstette

分布式優先體驗重現

Distributed prioritized experience replay

作者：Daniel Horgan, John Quan, David Budden, Gabriel Barth-maron, Matteo Hessel, Hado van Hasselt, David Silver

The Reactor：一個用於強化學習的快速、高效的表現「評論家「

The Reactor: A fast and sample-efficient actor-critic agent for reinforcement learning

作者：Audrunas Gruslys, Will Dabney, Mohammad Gheshlaghi Azar, Bilal Piot, Marc G Bellemare, Remi Munos

關於單一方向泛化的重要性

On the importance of single directions for generalization

作者：Ari Morcos, David GT Barrett, Neil C Rabinowitz, Matthew Botvinick

循環神經網絡語言模型中的內存架構

Memory architectures in recurrent neural network language models

作者：Dani Yogatama, Yishu Miao, Gábor Melis, Wang Ling, Adhiguna Kuncoro, Chris Dyer, Phil Blunsom

few-shot自回歸密度估計：學習如何學習分布

Few-shot autoregressive density estimation: Towards learning to learn distributions

作者：Scott Reed, Yutian Chen, Thomas Paine, Aaron van den Oord, S. M. Ali Eslami, Danilo J Rezende, Oriol Vinyals, Nando de Freitas

最優神經網絡模型的評估

On the state of the art of evaluation in neural language models

作者：Gábor Melis, Chris Dyer, Phil Blunsom

通過談判的緊急溝通

Emergent communication through negotiation

作者：Kris Cao, Angeliki Lazaridou, Marc Lanctot, Joel Z Leibo, Karl Tuyls, Stephen Clark

基於原始視覺輸入的組合式通信學習

Compositional obverter communication learning from raw visual input

作者：Edward Choi, Angeliki Lazaridou, Nando de Freitas

噪聲勘探網絡

Noisy networks for exploration

作者：Meire Fortunato, Mohammad Gheshlaghi Azar, Bilal Piot, Jacob Menick, Matteo Hessel, Ian Osband, Alex Graves, Volodymyr Mnih, Remi Munos, Demis Hassabis, Olivier Pietquin, Charles Blundell, Shane Legg

谷歌ICLR 2018論文集

在神經網絡和深度學習技術創新的前沿，谷歌專注於理論和應用研究，開發用於理解和概括的學習方法。作為ICLR 2018的白金贊助商，谷歌將有超過130名研究人員參加組委會和研討會，通過提交論文和海報，為更廣泛的學術研究社區作出貢獻和向其學習。

下面的列表是谷歌在ICLR 2018上展示的研究成果：

口頭報告：

Wasserstein Auto-Encoders

Ilya Tolstikhin，Olivier Bousquet，Sylvain Gelly，Bernhard Scholkopf

On the Convergence of Adam and Beyond (Best Paper Award)

關於 Adam 算法收斂性及其改進方法的討論（最佳論文獎）

作者：Sashank J. Reddi, Satyen Kale, Sanjiv Kumar

Ask the Right Questions: Active Question Reformulation with Reinforcement Learning

提出正確的問題：用強化學習激活問題的重構

作者：Christian Buck, Jannis Bulian, Massimiliano Ciaramita, Wojciech Gajewski, Andrea Gesmundo, Neil Houlsby, Wei Wang

Beyond Word Importance: Contextual Decompositions to Extract Interactions from LSTMs

超越單詞重要性：在 LSTM 中用語境分解推斷單詞之間的相互作用

作者：W. James Murdoch, Peter J. Liu, Bin Yu

大會Poster列表：

Boosting the Actor with Dual Critic

Bo Dai, Albert Shaw, Niao He, Lihong Li, Le Song

MaskGAN: Better Text Generation via Filling in the _______

MaskGAN：通過填寫_______更好地生成文本

William Fedus, Ian Goodfellow, Andrew M. Dai

Scalable Private Learning with PATE

用PATE進行可擴展的私人化學習

Nicolas Papernot, Shuang Song, Ilya Mironov, Ananth Raghunathan, Kunal Talwar, Ulfar Erlingsson

Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training

深度梯度壓縮：降低分布式訓練的通信帶寬

Yujun Lin, Song Han, Huizi Mao, Yu Wang, William J. Dally

Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches

Flipout：Mini-Batches上的高效偽獨立權重擾動

Yeming Wen, Paul Vicol, Jimmy Ba, Dustin Tran, Roger Grosse

Latent Constraints: Learning to Generate Conditionally from Unconditional Generative Models

潛在約束：學習從無條件生成模型實現有條件生成

Adam Roberts, Jesse Engel, Matt Hoffman

Multi-Mention Learning for Reading Comprehension with Neural Cascades

利用神經級聯進行閱讀理解的多義學習

Swabha Swayamdipta, Ankur P. Parikh, Tom Kwiatkowski

QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension

QANet：結合局部卷積與全局Self-Attention進行閱讀理解

Adams Wei Yu, David Dohan, Thang Luong, Rui Zhao, Kai Chen, Mohammad Norouzi, Quoc V. Le

Sensitivity and Generalization in Neural Networks: An Empirical Study

神經網絡的靈敏度與泛化：實證研究

Roman Novak, Yasaman Bahri, Daniel A. Abolafia, Jeffrey Pennington, Jascha Sohl-Dickstein

Action-dependent Control Variates for Policy Optimization via Stein Identity

通過Stein Identity進行策略優化的動作相關控制變量

Hao Liu, Yihao Feng, Yi Mao, Dengyong Zhou, Jian Peng, Qiang Liu

An Efficient Framework for Learning Sentence Representations

學習句子表示的一個有效框架

Lajanugen Logeswaran, Honglak Lee

Fidelity-Weighted Learning

Mostafa Dehghani, Arash Mehrjou, Stephan Gouws, Jaap Kamps, Bernhard Schölkopf

Generating Wikipedia by Summarizing Long Sequences

通過總結長序列生成維基百科

Peter J. Liu, Mohammad Saleh, Etienne Pot, Ben Goodrich, Ryan Sepassi, Lukasz Kaiser, Noam Shazeer

Matrix Capsules with EM Routing

Geoffrey Hinton, Sara Sabour, Nicholas Frosst

Temporal Difference Models: Model-Free Deep RL for Model-Based Control

時間差異模型：無模型深度RL用於基於模型的控制

Sergey Levine, Shixiang Gu, Murtaza Dalal, Vitchyr Pong

Deep Neural Networks as Gaussian Processes

作為高斯過程的深度神經網絡

Jaehoon Lee, Yasaman Bahri, Roman Novak, Samuel L. Schoenholz, Jeffrey Pennington, Jascha Sohl-Dickstein

Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence at Every Step

多路徑平衡：GAN不需要逐步減少散度

William Fedus, Mihaela Rosca, Balaji Lakshminarayanan, Andrew M. Dai, Shakir Mohamed,Ian Goodfellow

Initialization Matters: Orthogonal Predictive State Recurrent Neural Networks

初始化問題：正交預測狀態遞歸神經網絡

Krzysztof Choromanski, Carlton Downey, Byron Boots

Learning Differentially Private Recurrent Language Models

H. Brendan McMahan, Daniel Ramage, Kunal Talwar, Li Zhang

Learning Latent Permutations with Gumbel-Sinkhorn Networks

用Gumbel-Sinkhorn網絡學習潛在排列

Gonzalo Mena, David Belanger, Scott Linderman, Jasper Snoek

Leave no Trace: Learning to Reset for Safe and Autonomous Reinforcement Learning

不留痕跡：學習重置以實現安全和自主的強化學習

Benjamin Eysenbach, Shixiang Gu, Julian Ibarz, Sergey Levine

Meta-Learning for Semi-Supervised Few-Shot Classification

用於半監督的Few-Shot分類的元學習

Mengye Ren, Eleni Triantafillou, Sachin Ravi, Jake Snell, Kevin Swersky, Josh Tenenbaum,Hugo Larochelle, Richard Zemel

Thermometer Encoding: One Hot Way to Resist Adversarial Examples

Jacob Buckman, Aurko Roy, Colin Raffel, Ian Goodfellow

A Hierarchical Model for Device Placement

設備布局的分層模型

Azalia Mirhoseini, Anna Goldie, Hieu Pham, Benoit Steiner, Quoc V. Le, Jeff Dean

Monotonic Chunkwise Attention

Chung-Cheng Chiu, Colin Raffel

Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples

訓練置信度校準分類器用於檢測超出分配樣本

Kimin Lee, Honglak Lee, Kibok Lee, Jinwoo Shin

Trust-PCL: An Off-Policy Trust Region Method for Continuous Control

Trust-PCL：用於連續控制的 Off-Policy 信任域方法

Ofir Nachum, Mohammad Norouzi, Kelvin Xu, Dale Schuurmans

Ensemble Adversarial Training: Attacks and Defenses

Ensemble對抗訓練：攻擊和防禦

Florian Tramèr, Alexey Kurakin, Nicolas Papernot, Ian Goodfellow, Dan Boneh, Patrick McDaniel

Stochastic Variational Video Prediction

隨機變分視頻預測

Mohammad Babaeizadeh, Chelsea Finn, Dumitru Erhan, Roy Campbell, Sergey Levine

Depthwise Separable Convolutions for Neural Machine Translation

神經機器翻譯的深度可分卷積

Lukasz Kaiser, Aidan N. Gomez, Francois Chollet

Don’t Decay the Learning Rate, Increase the Batch Size

Samuel L. Smith, Pieter-Jan Kindermans, Chris Ying, Quoc V. Le

Generative Models of Visually Grounded Imagination

Ramakrishna Vedantam, Ian Fischer, Jonathan Huang, Kevin Murphy

Large Scale Distributed Neural Network Training through Online Distillation

通過 Online Distillation 進行大規模分布式神經網絡訓練

Rohan Anil, Gabriel Pereyra, Alexandre Passos, Robert Ormandi, George E. Dahl, Geoffrey E. Hinton

Learning a Neural Response Metric for Retinal Prosthesis

Nishal P. Shah, Sasidhar Madugula, Alan Litke, Alexander Sher, EJ Chichilnisky, Yoram Singer,Jonathon Shlens

Neumann Optimizer: A Practical Optimization Algorithm for Deep Neural Networks

Neumann優化器：一種用於深度神經網絡的實用優化算法

Shankar Krishnan, Ying Xiao, Rif A. Saurous

A Neural Representation of Sketch Drawings

素描圖的神經表示

David Ha, Douglas Eck

Deep Bayesian Bandits Showdown: An Empirical Comparison of Bayesian Deep Networks for Thompson Sampling

Carlos Riquelme, George Tucker, Jasper Snoek

Generalizing Hamiltonian Monte Carlo with Neural Networks

Daniel Levy, Matthew D. Hoffman, Jascha Sohl-Dickstein

Leveraging Grammar and Reinforcement Learning for Neural Program Synthesis

利用語法和強化學習進行神經程序綜合

Rudy Bunel, Matthew Hausknecht, Jacob Devlin, Rishabh Singh, Pushmeet Kohli

On the Discrimination-Generalization Tradeoff in GANs

論GAN中的Discrimination-Generalization權衡

Pengchuan Zhang, Qiang Liu, Dengyong Zhou, Tao Xu, Xiaodong He

A Bayesian Perspective on Generalization and Stochastic Gradient Descent

關於泛化和隨機梯度下降的貝葉斯觀點

Samuel L. Smith, Quoc V. Le

Learning how to Explain Neural Networks: PatternNet and PatternAttribution

學習如何解釋神經網絡：PatternNet和PatternAttribution

Pieter-Jan Kindermans, Kristof T. Schütt, Maximilian Alber, Klaus-Robert Müller, Dumitru Erhan, Been Kim, Sven Dähne

Skip RNN: Learning to Skip State Updates in Recurrent Neural Networks

Skip RNN：學習在遞歸神經網絡中跳過狀態更新

Víctor Campos, Brendan Jou, Xavier Giró-i-Nieto, Jordi Torres, Shih-Fu Chang

Towards Neural Phrase-based Machine Translation

基於神經短語的機器翻譯

Po-Sen Huang, Chong Wang, Sitao Huang, Dengyong Zhou, Li Deng

Unsupervised Cipher Cracking Using Discrete GANs

使用離散GAN的無監督密碼破譯

Aidan N. Gomez, Sicong Huang, Ivan Zhang, Bryan M. Li, Muhammad Osama, Lukasz Kaiser

Variational Image Compression With A Scale Hyperprior

利用一個Scale Hyperprior進行變分圖像壓縮

Johannes Ballé, David Minnen, Saurabh Singh, Sung Jin Hwang, Nick Johnston

Workshop Posters列表

Local Explanation Methods for Deep Neural Networks Lack Sensitivity to Parameter Values

Julius Adebayo, Justin Gilmer, Ian Goodfellow, Been Kim

Stoachastic Gradient Langevin Dynamics that Exploit Neural Network Structure

Zachary Nado, Jasper Snoek, Bowen Xu, Roger Grosse, David Duvenaud, James Martens

Towards Mixed-initiative generation of multi-channel sequential structure

Anna Huang, Sherol Chen, Mark J. Nelson, Douglas Eck

Can Deep Reinforcement Learning Solve Erdos-Selfridge-Spencer Games?

Maithra Raghu, Alex Irpan, Jacob Andreas, Robert Kleinberg, Quoc V. Le, Jon Kleinberg

GILBO: One Metric to Measure Them All

Alexander Alemi, Ian Fischer

HoME: a Household Multimodal Environment

Simon Brodeur, Ethan Perez, Ankesh Anand, Florian Golemo, Luca Celotti, Florian Strub, Jean Rouat, Hugo Larochelle, Aaron Courville

Learning to Learn without Labels

Luke Metz, Niru Maheswaranathan, Brian Cheung, Jascha Sohl-Dickstein

Learning via Social Awareness: Improving Sketch Representations with Facial Feedback

Natasha Jaques, Jesse Engel, David Ha, Fred Bertsch, Rosalind Picard, Douglas Eck

Negative Eigenvalues of the Hessian in Deep Neural Networks

Guillaume Alain, Nicolas Le Roux, Pierre-Antoine Manzagol

Realistic Evaluation of Semi-Supervised Learning Algorithms

Avital Oliver, Augustus Odena, Colin Raffel, Ekin Cubuk, lan Goodfellow

Winner's Curse? On Pace, Progress, and Empirical Rigor

D. Sculley, Jasper Snoek, Alex Wiltschko, Ali Rahimi

Meta-Learning for Batch Mode Active Learning

Sachin Ravi, Hugo Larochelle

To Prune, or Not to Prune: Exploring the Efficacy of Pruning for Model Compression

Michael Zhu, Suyog Gupta

Adversarial Spheres

Justin Gilmer, Luke Metz, Fartash Faghri, Sam Schoenholz, Maithra Raghu,,Martin Wattenberg, Ian Goodfellow

Clustering Meets Implicit Generative Models

Francesco Locatello, Damien Vincent, Ilya Tolstikhin, Gunnar Ratsch, Sylvain Gelly, Bernhard Scholkopf

Decoding Decoders: Finding Optimal Representation Spaces for Unsupervised Similarity Tasks

Vitalii Zhelezniak, Dan Busbridge, April Shen, Samuel L. Smith, Nils Y. Hammerla

Learning Longer-term Dependencies in RNNs with Auxiliary Losses

Trieu Trinh, Quoc Le, Andrew Dai, Thang Luong

Graph Partition Neural Networks for Semi-Supervised Classification

Alexander Gaunt, Danny Tarlow, Marc Brockschmidt, Raquel Urtasun, Renjie Liao, Richard Zemel

Searching for Activation Functions

Prajit Ramachandran, Barret Zoph, Quoc Le

Time-Dependent Representation for Neural Event Sequence Prediction

Yang Li, Nan Du, Samy Bengio

Faster Discovery of Neural Architectures by Searching for Paths in a Large Model

Hieu Pham, Melody Guan, Barret Zoph, Quoc V. Le, Jeff Dean

Intriguing Properties of Adversarial Examples

Ekin Dogus Cubuk, Barret Zoph, Sam Schoenholz, Quoc Le

PPP-Net: Platform-aware Progressive Search for Pareto-optimal Neural Architectures

Jin-Dong Dong, An-Chieh Cheng, Da-Cheng Juan, Wei Wei, Min Sun

The Mirage of Action-Dependent Baselines in Reinforcement Learning

George Tucker, Surya Bhupatiraju, Shixiang Gu, Richard E. Turner, Zoubin Ghahramani,Sergey Levine

Learning to Organize Knowledge with N-Gram Machines

Fan Yang, Jiazhong Nie, William W. Cohen, Ni Lao

Online variance-reducing optimization

Nicolas Le Roux, Reza Babanezhad, Pierre-Antoine Manzagol

返回搜狐，查看更多

責任編輯：