原標題：機器學習領域各領域必讀經典綜述論文整理分享

機器學習是一門多領域交叉學科，涉及概率論、統計學、逼近論、凸分析、算法復雜度理論等多門學科。專門研究計算機怎樣模擬或實現人類的學習行為，以獲取新的知識或技能，重新組織已有的知識結構使之不斷改善自身的性能。

機器學習及其相關領域，如深度學習、自然語言處理、計算機視覺、推薦系統、強化學習等領域最近幾年非常火，每年各式各樣的國際頂會，投稿數每年都會海量增加。要持續Follow這些領域最新的技術，刷遍各大會議最新會議非常費時費力，特別是對于剛入門的同學。因此，為了方便同學們了解機器學習、AI各領域的最新的技術全貌，本資源整理了各領域必讀的經典綜述論文，分享給大家。

資源整理自網絡，源地址：https://github.com/eugeneyan/ml-surveys

目錄

推薦系統

?Algorithms: Recommender systems survey

?Algorithms: Deep Learning based Recommender System: A Survey and New Perspectives

?Algorithms: Are We Really Making Progress? A Worrying Analysis of Neural Recommendation Approaches

?Serendipity: A Survey of Serendipity in Recommender Systems

?Diversity: Diversity in Recommender Systems – A survey

?Explanations: A Survey of Explanations in Recommender Systems

深度學習

?Architecture: A State-of-the-Art Survey on Deep Learning Theory and Architectures

?Knowledge distillation: Knowledge Distillation: A Survey

?Model compression: Compression of Deep Learning Models for Text: A Survey

?Transfer learning: A Survey on Deep Transfer Learning

?Neural architecture search: A Comprehensive Survey of Neural Architecture Search-- Challenges and Solutions

?Neural architecture search: Neural Architecture Search: A Survey

自然語言處理

?Deep Learning: Recent Trends in Deep Learning Based Natural Language Processing

?Classification: Deep Learning Based Text Classification: A Comprehensive Review

?Generation: Survey of the SOTA in Natural Language Generation: Core tasks, applications and evaluation

?Generation: Neural Language Generation: Formulation, Methods, and Evaluation

?Transfer learning: Exploring Transfer Learning with T5: the Text-To-Text Transfer Transformer (Paper)

?Metrics: Beyond Accuracy: Behavioral Testing of NLP Models with CheckList

?Metrics: Evaluation of Text Generation: A Survey

計算機視覺

?Object detection: Object Detection in 20 Years

?Adversarial attacks: Threat of Adversarial Attacks on Deep Learning in Computer Vision

?Autonomous vehicles: Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Art

深度強化學習

?Algorithms: A Brief Survey of Deep Reinforcement Learning

?Transfer learning: Transfer Learning for Reinforcement Learning Domains

?Economics: Review of Deep Reinforcement Learning Methods and Applications in Economics

向量化技術

?Graph: A Comprehensive Survey of Graph Embedding: Problems, Techniques and Applications

?Text: From Word to Sense Embeddings:A Survey on Vector Representations of Meaning

?Text: Diachronic Word Embeddings and Semantic Shifts

?Text: Word Embeddings: A Survey

Meta-learning and Few-shot Learning

?NLP: Meta-learning for Few-shot Natural Language Processing: A Survey

?Domain Agnostic: Learning from Few Samples: A Survey

?NN: Meta-Learning in Neural Networks: A Survey

?Domain Agnostic: A Comprehensive Overview and Survey of Recent Advances in Meta-Learning

?Domain Agnostic: Baby steps towards few-shot learning with multiple semantics

?Domain Agnostic: Meta-Learning: A Survey

?Domain Agnostic: A Perspective View And Survey Of Meta-learning

遷移學習

?Transfer learning: A Survey on Transfer Learning

免責申明:本站所有內容均來自網絡,我們對文中觀點保持中立,對所包含內容的準確性,可靠性或者完整性不提供任何明示或暗示的保證,請僅作參考。若有侵權,請聯系刪除。

文章來源：深度學習與NLP返回搜狐，查看更多

責任編輯：