強勢圍觀ICML2018,假裝去北歐避暑(附621篇論文下載)

强势围观ICML2018,假装去北欧避暑(附621篇论文下载)

「將門×行業龍頭企業創新行」

將門作為一家以技術創新為切入口的早期創新發掘機構,重磅啟動「將門×行業龍頭企業創新行」計劃,邀請各地技術小夥伴們一同走入來自零售、交通、醫療、金融、地產等行業龍頭企業,深入理解AI落地場景,發掘更多AI價值的應用空間。

7月20日(週五)的首站,我“門”將來到全球醫療健康領域的領導者—飛利浦。我們也很榮幸邀請到飛利浦人工智能實驗室總監周子捷博士,屆時他將到場和大家分享“飛利浦人工智能驅動的醫療解決方案”,介紹飛利浦在“人工智能應用於醫療健康”領域的研究方向和創新成果。戳我來報名

整理:T.R

參考:ICML018 https://icml.cc/Conferences/2018

强势围观ICML2018,假装去北欧避暑(附621篇论文下载)

一年一度的國際機器學習會議ICML已於10號在瑞典的斯德哥爾摩召開。七月的酷暑裡在讀ICML2018的論文,彷彿就像從遙遠的北歐彷彿吹來了陣陣清風。今年的ICML共接收論文621篇

【一鍵下載所有論文】T.R同學的論文下載工具>>https://pan.baidu.com/s/1CHNPpyF77EXBbVzwKxa_tw

强势围观ICML2018,假装去北欧避暑(附621篇论文下载)

上圖是ICML論文題目的詞雲,其中Learn和Network依然是會議的主題。

同時還包括了9個tutorial,四場主題演講涵蓋了安全、效率、交互和類人智能等方面。此外還包含了75個workshop,為與會者們提供了各個領域豐富的交流機會。下面就讓我們來看看都有哪些有趣的workshop吧!

音樂

機器學習最終要用於人社會的生產生活中才能為人類造福。科學家們一直在探索機器學習對於精神文明建設的作用。AI已經可以分析和生成各種形式的藝術作品了。在今年的ICML會議中,舉辦了一個Machine Learning for Music的workshop來探討機器學習與音樂方面的問題。目前大規模的在線音樂曲庫對於機器學習提出了新的要求,需要算法和模型能夠高效地理解和組織複雜的數據。

强势围观ICML2018,假装去北欧避暑(附621篇论文下载)

除了成熟的推薦系統外,還需要研究音樂生成和音頻處理方面所面臨的挑戰。同時包括音樂的表示學習、自動打標、音樂合成及風格轉換等都將在workshop中進行探討。

强势围观ICML2018,假装去北欧避暑(附621篇论文下载)

https://sites.google.com/site/faimmusic2018/

人性化

人類一直希望能創造出和自己一樣的智慧機器,在人與機器之間建立更為牢固的夥伴關係。但其中的關鍵在於我們需要從現在需要人去理解機器的世界,發展到未來機器能理解人的世界中去。另一個workshop著重於對人性化AI的探討,目前人們都重視機器的智力水平,而忽略了它的情商高低。研究人員們希望通過這個workshop構建智能機器IQ和EQ之間的橋樑,並讓更多的人關注和研究這一領域。

强势围观ICML2018,假装去北欧避暑(附621篇论文下载)

研討會中不僅會介紹情感和和人性化對於機器智能的重要性,更從學習和想象的方面探討了AI的可能性。

强势围观ICML2018,假装去北欧避暑(附621篇论文下载)

https://www.humanizing-ai.com/

遊戲

相信各位小夥伴一定還記得不久前AI在DOTA中打敗了人類玩家,遊戲也是人工智能的發展一個重要的體現窗口,畢竟我們在嬰兒時期都是通過不斷地遊戲來習得對這個世界最初的經驗的。

强势围观ICML2018,假装去北欧避暑(附621篇论文下载)

這次研討會同樣舉辦了關於電子遊戲機器學習workshop,主要包括了蒙特卡洛方法、深度學習、強化學習、啟發式搜索、棋牌類遊戲、視頻遊戲、多人協作和遊戲理論等方面。相信研究人員們又回拋出令人驚奇的遊戲AI,繼續在各大遊戲中馳騁。

强势围观ICML2018,假装去北欧避暑(附621篇论文下载)

http://www.lamsade.dauphine.fr/~cazenave/cgw2018/cgw2018.html

IOT

隨著智能設備的發展IOT的重要性愈加凸顯,同可穿戴設備、環境傳感器到各種家居設備都需要IOT發揮強大的作用,近年來邊緣計算也應運而生。這些設備產生的海量數據比社交數據的速度快兩倍達到了44E Bytes/month。IOT設備主要是時序特徵的數據音視頻信息,但很多的數據目前還處於尚未被利用的狀態。AI4IOT研討會希望探討如何利用AI來理解這些數據,如何將物理系統與環境銜接起來,幫助人類依據IOT進行決策和行為。

强势围观ICML2018,假装去北欧避暑(附621篇论文下载)

包括提出相關的建模、分析方法,高效處理大規模數據的手段以及一定程度的預測和行為識別、異常檢測等方面。

强势围观ICML2018,假装去北欧避暑(附621篇论文下载)

https://www.zurich.ibm.com/AI4IoT/index.html

AutoML

機器學習非常成功,但目前還在很大程度上依賴人類專家的經驗來選擇架構調節參數。隨著技術的發展,機器學習算法逐漸發展成了易用便捷無需專業知識介入構建過程。Workshop on Automatic Machine研討會就著重探討自動機器學習領域的最新進展,包括研究平臺、遷移學習、表象、算法進化和新架構、加速、大規模計算等等方面。

强势围观ICML2018,假装去北欧避暑(附621篇论文下载)强势围观ICML2018,假装去北欧避暑(附621篇论文下载)

如果你想要深入瞭解,組委會還用心的提供了一份超詳細的教程來學習AutoML>>https://sites.google.com/site/automl2017ecmlpkdd/tutorial

除此之外還有包括因果推理、自動行為、計算幾何、生物、健康、視覺、感知、強化學習等等各方面共75個workshop,我們一併總結在下表中,如果有感興趣的可以點擊下面的網站找到對應的條目詳細瞭解。

https://icml.cc/Conferences/2018/Schedule?type=Workshop

31st International Workshop on Qualitative Reasoning (QR 2018)

6th Goal Reasoning Workshop

Computer Games Workshop

FCA4AI 2018

Joint Workshop on AI in Health (day 1)

Linguistic and Cognitive Approaches To Dialog Agents (LaCATODA 2018)

Tenth International Workshop Modelling and Reasoning in Context (MRC)

The 3rd International workshop on biomedical informatics with optimization and machine learning (BOOM)

The 3rd International Workshop on Knowledge Discovery in Healthcare Data

Towards learning with limited labels: Equivariance, Invariance, and Beyond

Fairness, Interpretability, and Explainability Federation of Workshops (day 1)

Autonomy in Teams -- Joint Workshop on Sharing Autonomy in Human-Robot Interaction

Learning and Reasoning: Principles & Applications to Everyday Spatial and Temporal Knowledge (day 1)

Cognitive Vision: Integrated Vision and AI for Embodied Perception and Interaction

Joint Workshop on AI in Health (day 2)

Learning and Reasoning: Principles & Applications to Everyday Spatial and Temporal Knowledge (day 2)

Fairness, Interpretability, and Explainability Federation of Workshops (day 2-3) (day 1)

10th International Workshop on Agents in Traffic and Transportation (ATT 2018)

19th International Workshop on Multi-Agent-Based Simulation (MABS 2018)

Adaptive and Learning Agents 2018 (day 1)

AI and Computational Psychology: Theories, Algorithms and Applications (CompPsy)

AI-MHRI (AI for Multimodal Human-Robot Interaction) (day 1)

ALAW - Agents Living in Augmented Worlds

AutoML 2018

Bridging the Gap between Human and Automated Reasoning

Data Science meets Optimization

Eighth International Workshop on Statistical Relational AI

Enabling Reproducibility in Machine Learning MLTrain@RML

Engineering Multi-Agent Systems (day 1)

First international workshop on socio-cognitive systems

Game-Theoretic Mechanisms for Data and Information

Goal Specifications for Reinforcement Learning

International Workshop on Automated Negotiation (ACAN)

International Workshop on Optimization in Multi-Agent Systems (OptMAS)

Joint ICML and IJCAI Workshop on Computational Biology 2018

Lifelong Learning: A Reinforcement Learning Approach

Modern Trends in Nonconvex Optimization for Machine Learning

The 2018 Joint Workshop on Machine Learning for Music

The AAMAS-IJCAI Workshop on Agents and Incentives in Artificial Intelligence (day 1)

Theoretical Foundations and Applications of Deep Generative Models (day 1)

Theory of Deep Learning

TRUST Workshop

Domain Adaptation for Visual Understanding

International Workshop on Massively Multi-Agent Systems

Workshop on Efficient Credit Assignment in Deep Learning and Deep Reinforcement Learning (ECA) (day 1)

Artificial Intelligence for Knowledge Management

Prediction and Generative Modeling in Reinforcement Learning

Privacy in Machine Learning and Artificial Intelligence (PiMLAI)

Fairness, Interpretability, and Explainability Federation of Workshops (day 2-3) (day 2)

International Workshop on Real Time compliant Multi-Agent Systems (RTcMAS)

2nd International Joint Conference on Artificial Intelligence (IJCAI) Workshop on Artificial Intelligence in Affective Computing

ABMUS-18 - Agent-Based Modelling of Urban Systems

Adaptive and Learning Agents 2018 (day 2)

AI for Aging, Rehabilitation and Independent Assisted Living (ARIAL) and Intelligent Conversation Agents in Home and Geriatric Care Applications

AI for Synthetic Biology 2

AI-MHRI (AI for Multimodal Human-Robot Interaction) (day 2)

Architectures and Evaluation for Generality, Autonomy and Progress in AI (AEGAP)

Engineering Multi-Agent Systems (day 2)

Exploration in Reinforcement Learning

Federated AI for Robotics Workshop (F-Rob-2018)

First Workshop on Deep Learning for Safety-Critical in Engineering Systems

Geometry in Machine Learning (GiMLi)

Humanizing AI (HAI)

Joint Workshop on Multimedia for Cooking and Eating Activities and Multimedia Assisted Dietary Management (CEA/MADiMa2018)

Machine learning for Causal Inference, Counterfactual Prediction, and Autonomous Action (CausalML)

Machine Learning: The Great Debates (MLGD2018)

Neural Abstract Machines & Program Induction Workshop v2.0 (NAMPI_v2)

Planning and Learning (PAL-18)

The AAMAS-IJCAI Workshop on Agents and Incentives in Artificial Intelligence (day 2)

The Joint International Workshop on Social Influence Analysis and Mining Actionable Insights from Social Networks (SocInf+MAISoN 2018)

Theoretical Foundations and Applications of Deep Generative Models (day 2)

Tractable Probabilistic Models

Workshop on Efficient Credit Assignment in Deep Learning and Deep Reinforcement Learning (ECA) (day 2)

Artificial Intelligence for Wildlife Conservation (AIWC) Workshop

Workshop on AI for Internet of Things

一些參考

https://wordart.com

https://icml.cc/Conferences/2018/Schedule?type=Workshop

http://metacreation.net/

-The End-

將門是一家專注於發掘、加速並投資技術創新激活商業價值的創業公司的新型創投機構,旗下設有將門創新服務、將門技術社群以及將門投資基金。

將門創新服務

專注於使創新的技術落地於真正的應用場景,激活和實現全新的商業價值,服務於行業領先企業和技術創新型創業公司。

將門技術社群專注於幫助技術創新型的創業公司提供來自產、學、研、創領域的核心技術專家的技術分享和學習內容,使創新成為持續的核心競爭力。

將門投資基金專注於投資通過技術創新激活商業場景,實現商業價值的初創企業,關注技術領域包括機器智能、物聯網、自然人機交互、企業計算。在兩年的時間裡,將門投資基金已經投資了包括量化派、碼隆科技、禾賽科技、景馳科技、杉數科技、迪英加科技等數十傢俱有高成長潛力的技術型創業公司。

如果您是技術領域的初創企業,不僅想獲得投資,還希望獲得一系列持續性、有價值的投後服務,歡迎發送或者推薦項目給我“門”: [email protected]

强势围观ICML2018,假装去北欧避暑(附621篇论文下载)

點擊右上角,把文章朋友圈

將門創投

讓創新獲得認可!

[email protected]


分享到:


相關文章: