机器学习领域各领域必读经典综述论文整理分享_scdn机器学习数据分析论文

    机器学习是一门多领域交叉学科，涉及概率论、统计学、逼近论、凸分析、算法复杂度理论等多门学科。专门研究计算机怎样模拟或实现人类的学习行为，以获取新的知识或技能，重新组织已有的知识结构使之不断改善自身的性能。

     

    机器学习及其相关领域，如深度学习、自然语言处理、计算机视觉、推荐系统、强化学习等领域最近几年非常火，每年各式各样的国际顶会，投稿数每年都会海量增加。要持续Follow这些领域最新的技术，刷遍各大会议最新会议非常费时费力，特别是对于刚入门的同学。因此，为了方便同学们了解机器学习、AI各领域的最新的技术全貌，本资源整理了各领域必读的经典综述论文，分享给大家。

    资源整理自网络，源地址：https://github.com/eugeneyan/ml-surveys

目录

推荐系统

    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

深度学习

    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

自然语言处理

    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

计算机视觉

    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

深度强化学习

    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

向量化技术

    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

迁移学习

    Transfer learning: A Survey on Transfer Learning

往期精品内容推荐

机器学习基础教材-《数据驱动的科学与工程-机器学习、动态系统与控制》免费pdf分享

2020年8月新书-《机器学习角度-因果推理算法介绍》免费pdf分享

计算机视觉（CV）历史最全预训练模型(部署)汇集分享

密歇根大学Justin Johnson-《深度学习与计算机视觉》课程视频及ppt分享

2020年最全-少样本学习（FSL）相关综述、数据集、模型/算法和应用资源整理分享

新书-《Bandit问题-基础、算法、理论、应用》分享

Yann LeCun-纽约大学2020 -《深度学习(pytorch)》中英字幕视频及ppt分享

DeepMind 2020年新课-《强化学习进阶课程》视频分享

2020年哥伦比亚大学新课-《经济学与AI及优化》课程分享