干货|专知2020-02推荐清单

科研宝典

Posted by JoselynZhao on March 3, 2020

2020

2月

  1. 【2020新书】深度学习视觉系统,Deep Learning for Vision Systems, 396页pdf image
  2. 从信息社会迈向智能社会,高文,北京大学教授、中国工程院院士,黄铁军为北京大学教授) 从信息社会迈向智能社会-中共中央网络安全和信息化委员会办公室

  3. 2020科技、传媒和电信行业预测,140页pdf https://www2.deloitte.com/content/dam/Deloitte/cn/…
  4. Autoencoders with Keras, TensorFlow, and Deep Learning Autoencoders with Keras, TensorFlow, and Deep Lear… image

  5. ‘从图(Graph)到图卷积(Graph Convolution): 漫谈图神经网络 - A blog for understanding graph neural network’ by Qian GitHub: https://github.com/SivilTaram/Graph-Neural-Network… 从图(Graph)到图卷积(Graph Convolution):漫谈图神经网络模型 (一) - S… image

  6. 【ICLR-2020】网络反卷积,NETWORK DECONVOLUTION https://arxiv.org/pdf/1905.11926.pdf image

  7. 【加州伯克利】真实数据科学,Veridical data science https://www.pnas.org/content/pnas/early/2020/02/12… image

  8. 【联邦学习相关文献资源大列表】’Awesome Federated Learning - list of resources for federated learning and privacy in machine learning’ by Poga Po GitHub: GitHub - poga/awesome-federated-learning: list of … image

  9. 【ICLR2020-】基于记忆的图网络,MEMORY-BASED GRAPH NETWORKS https://openreview.net/pdf?id=r1laNeBYPB image

  10. 【中科院计算所】深几何学习综述:从表征的角度, https://arxiv.org/pdf/2002.07995.pdf image

  11. 【纽约大学】贝叶斯深度学习和概率论的观点,27页pdf,Bayesian Deep Learning and a Probabilistic Perspective of Generalization https://arxiv.org/pdf/2002.08791.pdf image

  12. 分子注意力Transformer https://arxiv.org/pdf/2002.08264.pdf image

  13. 图像分类中的半监督、自监督和非监督技术综述相同点,不同点和组合 https://arxiv.org/pdf/2002.08721.pdf image

  14. 可解释机器学习 中文版翻译 GitHub - apachecn/interpretable-ml-book-zh: interp…

  15. 深度学习的主动学习概述,Overview of Active Learning for Deep Learning Overview of Active Learning for Deep Learning image

  16. 【南京大学吴建鑫教授-模式识别2020课程】 模式识别课程

  17. 【南京大学吴建鑫教授-卷积神经网络笔记】Convolutional neural networks image
  18. 【2020新书】算法与数据结构实战,286页pdf,Algorithms Data Structures in Action Manning | Algorithms and Data Structures in Action image

  19. 【MIT】图神经网络的泛化与表示极限,《Generalization and Representational Limits of Graph Neural Networks》V K. Garg, S Jegelka, T Jaakkola [CSAIL, MIT] (2020) [2002.06157] Generalization and Representational L… image

  20. 【MIT】成对判别器对抗训练的好处,The Benefits of Pairwise Discriminators for Adversarial Training https://arxiv.org/pdf/2002.08621.pdf

  21. C++17标准新书,109页pdf https://lp.embarcadero.com/Cpp17eBook image

  22. 《可解释的机器学习-interpretable-ml》238页pdf GitHub - apachecn/interpretable-ml-book-zh: interp… image

  23. 挽救毕业论文的三条“锦囊”:用读者的视角改摘要、用摘要的节奏改目录、带着质疑改分析。 1、用读者的视角改摘要。假设你是读者,看完后会有哪些能留下印象的工作?哪部分最有意思?那部分最深入?跳出卖家的自我,体会买家的挑剔,调整结构和节奏,给老师一个”不必细抠正文“的理由。 2、用摘要的节奏改目录。已经了解读者最看重哪里,在目录结构、章节标题方面稍加设计,将读者注意力引导到重点部分;标题仔细推敲,信息量要足够,而不仅仅是个索引,长度适中的条件下尽量体现你的角度、特色和侧重。 3、带着质疑改分析。重新审查实验结果分析部分,想想读者和答辩老师可能提出的质疑——数据来源、规模有说服力吗?差结果有没有讨论?比较的是否是真正的SOA方法?比较方式公平吗?分析结果如何呼应了论文标题?……未雨绸缪,多思考,多分析,多一份角度,就少一分破绽。

  24. 基于生成对抗网络的模仿学习综述 - 计算机学报 http://cjc.ict.ac.cn/online/onlinepaper/ljh-202011… image

  25. 【华南理工大学】无监督多类域自适应:理论、算法和实践,Unsupervised Multi-Class Domain Adaptation: Theory, Algorithms, and Practice https://arxiv.org/pdf/2002.08681.pdf image

  26. 【哈佛大学】机器学习的层次局限性,A Hierarchy of Limitations in Machine Learning https://arxiv.org/pdf/2002.05193.pdf image

  27. 【CVPR2020】用于细粒度动作识别的多模式域自适应,Multi-Modal Domain Adaptation for Fine-Grained Action Recognition [2001.09691] Multi-Modal Domain Adaptation for Fin… image

  28. 【CVPR2020】强化特征点,Reinforced Feature Points: Optimizing Feature Detection and Description for a High-Level Task https://arxiv.org/pdf/1912.00623.pdf image

  29. 【通往强人工智能之路途】A Road Map to Strong Intelligence https://arxiv.org/pdf/2002.09044.pdf I wrote this paper because technology can really improve people’s lives. With it, we can live longer in a healthy body, save time through increased efficiency and automation, and make better decisions. To get to the next level, we need to start looking at intelligence from a much broader perspective, and promote international interdisciplinary collaborations. Section 1 of this paper delves into sociology and social psychology to explain that the mechanisms underlying intelligence are inherently social. Section 2 proposes a method to classify intelligence, and describes the differences between weak and strong intelligence. Section 3 examines the Chinese Room argument from a different perspective. It demonstrates that a Turing-complete machine cannot have strong intelligence, and considers the modifications necessary for a computer to be intelligent and have understanding. Section 4 argues that the existential risk caused by the technological explosion of a single agent should not be of serious concern. Section 5 looks at the AI control problem and argues that it is impossible to build a super-intelligent machine that will do what it creators want. By using insights from biology, it also proposes a solution to the control problem. Section 6 discusses some of the implications of strong intelligence. Section 7 lists the main challenges with deep learning, and asserts that radical changes will be required to reach strong intelligence. Section 8 examines a neuroscience framework that could help explain how a cortical column works. Section 9 lays out the broad strokes of a road map towards strong intelligence. Finally, section 10 analyzes the impacts and the challenges of greater intelligence. image

  30. 【CVPR2020-加州理工大学Devi Parikh】多任务视觉和语言表达学习,12-in-1: Multi-Task Vision and Language Representation Learning [1912.02315] 12-in-1: Multi-Task Vision and Langua… image

  31. 遗传算法解释-Genetic Algorithms Explained : A Python Implementation Genetic Algorithms Explained : A Python Implementa… https://hackernoon.com/genetic-algorithms-explained-a-python-implementation-sd4w374i image

  32. 【经典书】算法设计与分析,727页pdf,Algorithms Design and Analysis Algorithms - Paperback - Harsh Bhasin - Oxford Uni… https://global.oup.com/ukhe/product/algorithms-9780199456666?cc=cn&lang=en& image

  33. 写在20年初的校招面试心得与自学CS经验及找工作分享 tips_for_interview/README-zh_CN.md at master · con… https://github.com/conanhujinming/tips_for_interview/blob/master/README-zh_CN.md image

  34. 贝叶斯网络在医疗的应用综述 https://arxiv.org/ftp/arxiv/papers/2002/2002.08627… image

  35. François Chollet:学新事物的最大障碍,在于当你还很不擅长的时候,很多东西看起来太无聊,而我们又只是在不断地打基础(比如数学)。你需要保持动力,直到你变得足够好,好到深入实践的乐趣足以提供持续动力。关于动力和坚持,游戏可以给我们一些启示:
    • 亲和力: 第一次尝试应该提供足够的乐趣,同时也带来挑战
    • 奖励
    • 快速的反馈回路
  36. 【图表示学习解析与实现】’Graph Representation Learning - PyTorch Implementation and Explanation of Graph Representation Learning papers involving DeepWalk, GCN, GraphSAGE, ChebNet & GAT.’ by Data Science Group, IIT Roorkee GitHub: GitHub - dsgiitr/graph_nets: PyTorch Implementatio… https://github.com/dsgiitr/graph_nets image

  37. 使用Python掌握数据挖掘, 269页pdf, Mastering Data Mining with Python image

  38. 算法技术手册,Algorithms in a Nutshell,333页pdf image
  39. 数据结构,第三版,Data Structures, 3rd Edition,Abstraction and Design Using Java image

  40. 终极算法,353页pdf,The Master Algorithm,How the Quest for the Ultimate Learning Machine Will Remake Our World image

  41. 数据挖掘:理论、算法和示例,347页pdf,Data Mining: Theories, Algorithms, and Examples image ==下载失败==

  42. 【2020新书】概率深度学习Python: MEAP of Probabilistic Deep Learning: With Python, Keras and TensorFlow Probability Manning | Probabilistic Deep Learning https://www.manning.com/books/probabilistic-deep-learning image

  43. 使用Python进行实际的机器学习,545页pdf,Practical Machine Learning with Python,A Problem-Solver’s Guide to Building Real-World Intelligent Systems image
  44. ‘LeetCode、剑指Offer刷题笔记(C/C++、Python3实现)’ by Jack Cui GitHub: GitHub - Jack-Cherish/LeetCode: LeetCode、剑指Offer刷题…https://github.com/Jack-Cherish/LeetCode image

  45. ‘labuladong 的算法小抄,总结各种常考算法的套路,助力刷题面试’ by labuladong GitHub: GitHub - labuladong/fucking-algorithm: labuladong … image

  46. 2019年人工智能发展白皮书,47页pdf https://www.cebnet.com.cn/upload/resources/file/20… image

  47. Google“面经”】《Tips for interviewing at Google | psc’s website》by Pablo Samuel Castro Tips for interviewing at Google | psc’s website https://psc-g.github.io/interviews/google/2020/02/25/interviewing-at-google.html image

  48. 多模态BERT,76页ppt,LXMERT: Learning Cross-Modality Encoder Representations from Transformers http://www.cs.unc.edu/~airsplay/EMNLP_2019LXMERT… GitHub - airsplay/lxmert: PyTorch code for EMNLP 2…https://github.com/airsplay/lxmert image

  49. 【Uber AI】持续元学习,Learning to Continually Learn https://arxiv.org/pdf/2002.09571.pdf image

  50. 人工智能中的对称性:从变换到对称的历史 (一)序言:什么是对称性? 人工智能中的对称性:从变换到对称的历史 (一)序言:什么是对称性? - 知乎 https://zhuanlan.zhihu.com/p/109207015 image

  51. ‘CVPR 2020 论文开源项目合集’ by Amusi GitHub: https://github.com/amusi/CVPR2020-Code image

  52. 【牛津大学ICLR2020】通过元学习的贝叶斯自适应深度RL, VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning https://openreview.net/pdf?id=Hkl9JlBYvr image

  53. 【CVPR 2020】Gatech- Out-of-distribution图像检测,Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Data https://arxiv.org/pdf/2002.11297.pdf image

  54. 离散分布简要笔记,A short note on learning discrete distributions https://arxiv.org/pdf/2002.11457.pdf

  55. 【CVPR2020-电子科大-南洋理工-阿里巴巴】视觉常识R-CNN,Visual Commonsense R-CNN https://arxiv.org/pdf/2002.12204.pdf image

  56. 【伯克利】深度学习多源领域自适应,Multi-source Domain Adaptation in the Deep Learning Era: A Systematic Survey https://arxiv.org/pdf/2002.12169.pdf image

  57. 填补空间域和光谱域之间的空白:图神经网络研究综述 https://arxiv.org/pdf/2002.11867.pdf image

58.【香港科技大学】联邦半监督学习,A Survey towards Federated Semi-supervised Learning https://arxiv.org/pdf/2002.11545.pdf image

  1. 贝叶斯非参数空间划分:综述,Bayesian Nonparametric Space Partitions: A Survey https://arxiv.org/pdf/2002.11394.pdf

  2. BERT论文合集,BERT-related papers GitHub - tomohideshibata/BERT-related-papers: BERT… https://github.com/tomohideshibata/BERT-related-papers image
  3. BERT到底如何work的?A Primer in BERTology: What we know about how BERT works https://arxiv.org/pdf/2002.12327.pdf image

  4. 北大张志华老师 机器学习 系列课程视频资源 http://www.math.pku.edu.cn/teachers/zhzhang/course… 《机器学习导论》 http://resource.pku.edu.cn/index.php?r=course/deta… 《统计机器学习》 http://resource.pku.edu.cn/index.php?r=course/deta… 《应用数学基础》(深度学习的数学基础) http://resource.pku.edu.cn/index.php?r=course/deta… 《强化学习基础》 http://resource.pku.edu.cn/index.php?r=course/deta…

image

  1. 元迁移学习的小样本学习,Meta-transfer Learning for Few-shot Learning https://yyliu.net/files/meta-transfer-learning-sli…

image

  1. Transductive Few-shot Learning with Meta-Learned Confidence https://128.84.21.199/pdf/2002.12017.pdf

  2. 滑铁卢大学,胶囊网络,https://cedar.buffalo.edu/~srihari/CSE676/9.12%20C…
  3. image
  4. [图解自监督学习】《The Illustrated Self-Supervised Learning》by Amit Chaudhary The Illustrated Self-Supervised Learning https://amitness.com/2020/02/illustrated-self-supervised-learning/ image

  5. 【贝叶斯规则因果推理】《Causal Inference with Bayes Rule》by Finn Lattimore, David Rohde Causal Inference with Bayes Rule - Gradient Instit… https://gradientinstitute.org/blog/6/

  6. 【微软雷德蒙研究院】小样本自然语言生成,Few-shot Natural Language Generation for Task-Oriented Dialog Few-shot Natural Language Generation for Task-Orie… https://www.arxiv-vanity.com/papers/2002.12328/ image

  7. 【自监督学习深度神经网络视觉特征学习综述论文】Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey [1902.06162] Self-supervised Visual Feature Learni… https://arxiv.org/abs/1902.06162 image

  8. 【Yoshua Bengio:深度学习认知】《Deep Learning Cognition | Full Keynote - AI in 2020 & Beyond - YouTube》by Yoshua Bengio https://www.youtube.com/watch?reload=9&v=GibjI5FoZ… image

  9. 【fastai新书《Deep Learning for Coders with fastai and PyTorch: AI Applications Without a PhD》草稿,fastai/PyTorch深度学习实战】’The fastai book - Draft of the fastai book’ by fastai GitHub: GitHub - fastai/fastbook: Draft of the fastai book https://github.com/fastai/fastbook image

  10. 【PyTorch深度学习学习与实践(Notebooks合集)】’PyTorch Notebooks - A collection of PyTorch notebooks for learning and practicing deep learning’ by dair.ai GitHub: GitHub - dair-ai/pytorch_notebooks: 🔥A collection … https://github.com/dair-ai/pytorch_notebooks image

  11. 【斯坦福大学-ICLR2020】图神经网络预训练的策略,Strategies for Pre-training Graph Neural Networks gnn-pretrain http://snap.stanford.edu/gnn-pretrain/ https://openreview.net/pdf?id=HJlWWJSFDH image

  12. 【加州大学-Liwei Wu博士论文】协同过滤与排序,Advances in Collaborative Filtering and Ranking,150页pdf https://arxiv.org/pdf/2002.12312.pdf image

  13. Transformers 是图神经网络?Graph Neural Networks Transformers are Graph Neural Networks | NTU Graph… https://graphdeeplearning.github.io/post/transformers-are-gnns/ image

  14. 资源受限设备端的联邦学习综述论文,Federated Learning for Resource-Constrained IoT Devices: Panoramas and State-of-the-art https://arxiv.org/pdf/2002.10610.pdf image