不僅是白金贊助商,谷歌更是ICML 2017 的重量級參與者(附59篇收錄論文下載) | ICML 2017

 2017-08-07 15:30:00.0

機器學習領域頂級會議 ICML 2017 已經開始了,我們記者會帶來全方位的大會報道。

在之前的文章中,我們就介紹過434篇 ICML 收錄論文中有多達44篇都出現了谷歌的名字,谷歌的在機器學習領域的投入與成果之多可見一斑。今天谷歌也正式給出了自己的收錄論文名單,署名的谷歌的就有42篇,其中有4篇是在幾個 workshop 中。根據我們前兩天的報道,署名DeepMind的收錄論文也有25篇之多。那麼來自谷歌的全部論文就有65篇(其中2篇是谷歌和DeepMind合作完成的),大約是 ICML 2017 全部收錄論文的七分之一。這個數字簡直大到讓人有點害怕了。

谷歌在文中說,機器學習是谷歌的重點戰略之一,他們有非常活躍的研究小組在領域內的各個方面進行研究,包括深度學習和更多的傳統算法,理論和應用探索並重。谷歌的研究人員們運用可拓展的工具和架構,構建出各種各樣的機器學習系統供他們解決語言、語音、翻譯、音樂、視覺處理等等方面艱深的科學和工程問題。

作爲機器學習領域的帶頭人之一,谷歌不僅是今年 ICML 2017的白金贊助商,也實實在在做出了許多研究成果(體現爲42篇接收論文),此次參加會議展示論文、組織workshop的研究人員也有130人之多,熱切地希望跟整個機器學習大家庭有更多的溝通和協作。

除了論文和workshop,谷歌的研究人員們還會對一些新的研究成果做講解和展示,比如介紹 Facets 背後的技術、音頻生成神經網絡 Nsynth,還會有一個關於谷歌大腦培訓生計劃的問答活動。

谷歌在文中給出了自己的42篇論文列表,感興趣的讀者可以具體關注一下,打包下載地址見文末

  • A Unified Maximum Likelihood Approach for Estimating Symmetric Properties of Discrete Distributions

  • Accelerating Eulerian Fluid Simulation With Convolutional Networks

  • AdaNet: Adaptive Structural Learning of Artificial Neural Networks

  • Adaptive Feature Selection: Computationally Efficient Online Sparse Linear Regression under RIP

  • Algorithms for ℓp Low-Rank Approximation

  • Axiomatic Attribution for Deep Networks

  • Bridging the Gap Between Value and Policy Based Reinforcement Learning

    • Lifelong Learning: A Reinforcement Learning Approach Workshop論文,workshop時間8月10日

  • Canopy Fast Sampling with Cover Trees

  • Conditional Image Synthesis with Auxiliary Classifier GANs

  • Consistent k-Clustering

  • Deep Value Networks Learn to Evaluate and Iteratively Refine Structured Outputs

  • Density Level Set Estimation on Manifolds with DBSCAN

  • Device Placement Optimization with Reinforcement Learning

  • Differentiable Programs with Neural Libraries

  • Distributed Mean Estimation with Limited Communication

  • Filtering Variational Objectives

    • Deep Structured Prediction Workshop論文,workshop時間8月11日

  • Generating High-Quality and Informative Conversation Responses with Sequence-to-Sequence Models

    • Learning to Generate Natural Language Workshop論文,workshop時間8月10日

  • Geometry of Neural Network Loss Surfaces via Random Matrix Theory

  • Gradient Boosted Decision Trees for High Dimensional Sparse Output

  • Input Switched Affine Networks: An RNN Architecture Designed for Interpretability

  • Large-Scale Evolution of Image Classifiers

  • Latent LSTM Allocation: Joint Clustering and Non-Linear Dynamic Modeling of Sequence Data

  • Learned Optimizers that Scale and Generalize

  • Learning Deep Latent Gaussian Models with Markov Chain Monte Carlo

  • Learning to Generate Long-term Future via Hierarchical Prediction

  • Maximum Selection and Ranking under Noisy Comparisons

  • Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders

    • 谷歌與DeepMind合作論文

  • Neural Message Passing for Quantum Chemistry

    • 谷歌與DeepMind合作論文

  • Neural Optimizer Search with Reinforcement Learning

  • On the Expressive Power of Deep Neural Networks

  • Online and Linear-Time Attention by Enforcing Monotonic Alignments

  • Probabilistic Submodular Maximization in Sub-Linear Time

  • REBAR: Low-variance unbiased gradient estimates for discrete latent variable models 

    • Deep Structured Prediction Workshop論文,workshop時間8月11日

  • Robust Adversarial Reinforcement Learning

  • RobustFill: Neural Program Learning under Noisy IO

  • Sequence Tutor: Conservative Fine-Tuning of Sequence Generation Models with KL-control

  • Sharp Minima Can Generalize For Deep Nets

  • Stochastic Generative Hashing

  • Tight Bounds for Approximate Carathéodory and Beyond

  • Uniform Convergence Rates for Kernel Density Estimation

  • Variational Boosting: Iteratively Refining Posterior Approximations

  • Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning

via Google Research Blog

42篇谷歌署名論文+17篇DeepMind署名演講論文打包下載鏈接: 

http://pan.baidu.com/s/1jIFYZqu   密碼: t74m

我們記者也已經在 ICML現場參與大會活動,更多報道請繼續關注。

相關文章:

太熱了,雷鋒網跑來悉尼避暑,順便爲你報道 ICML 2017

重磅 | ICML 2017最佳論文公佈!機器學習的可解釋性成熱點

文章來源:雷鋒網