前百度首席科学家吴恩达发表的史上最全论文合集(附下载)


吴恩达(英文名:Andrew Ng,1976年生)


斯坦福大学计算机科学系和电气工程系的副教授,斯坦福人工智能实验室的主任。他还与达芙妮·科勒一起创建了在线教育平台Coursera。


2011年,吴恩达在Google创建了GoogleBrain项目,以通过分布式集群计算机开发超大规模的人工神经网络。2014年5月16日,吴恩达加入百度,负责“百度大脑”计划,并担任百度公司首席科学家。2017年3月20日,吴恩达宣布从百度辞职。


相关阅读

重磅 ‖ 中国将在AI竞赛中超越美国?吴恩达如此回应...


机械鸡收录了到目前为止吴恩达教授的所有论文(1995-2017),文中因篇幅限制列出了2013-2017年吴发表的论文,获取完整版论文合集请回复关键词“NG”获取下载链接。


2017

 

Data Noising as Smoothing inNeural Network Language Models

PDF地址:https://arxiv.org/pdf/1703.02573.pdf 

 

Deep Voice: Real-time NeuralText-to-Speech

PDF地址:https://arxiv.org/pdf/1702.07825.pdf

 

2016

 

Autonomous Aerobatic Airplane Control with Reinforcement Learning

PDF地址:http://cs229.stanford.edu/proj2016/report/BecdelievrePouletBevillard-AerobaticsAircraftControllerwithReinforcementLearning-report.pdf

 

Deep Learning: What's Next

PDF地址:http://trust.sce.ntu.edu.sg/aamas16/pdfs/p1.pdf

 

Neural Language Correction withCharacter-Based Attention

PDF地址:https://arxiv.org/pdf/1603.09727.pdf

 

Speech Is 3x Faster than Typing forEnglish and Mandarin Text Entry on Mobile Devices

PDF地址:https://arxiv.org/pdf/1608.07323.pdf

 

Unsupervised deep learning applied tobreast density segmentation and mammographic risk scoring

PDF地址:http://image.diku.dk/igel/paper/UDLAtBDSaMRS.pdf

 

 

2015


An Empirical Evaluation of DeepLearning on Highway Driving

PDF地址:https://arxiv.org/pdf/1504.01716.pdf

 

Building DNN Acoustic Models forLarge Vocabulary Speech Recognition

PDF地址:https://arxiv.org/pdf/1406.7806.pdf

 

Deep Speech 2: End-to-End SpeechRecognition in English and Mandarin

PDF地址:https://arxiv.org/pdf/1512.02595.pdf

 

Driverseat: Crowdstrapping LearningTasks for Autonomous Driving

PDF地址:https://arxiv.org/pdf/1512.01872.pdf

 

End-to-end people detection incrowded scenes

PDF地址:http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Stewart_End-To-End_People_Detection_CVPR_2016_paper.pdf

 

Lexicon-Free Conversational SpeechRecognition with Neural Networks

PDF地址:http://www.aclweb.org/anthology/N15-1038

 

 

2014


Deep Speech: Scaling up end-to-endspeech recognition

PDF地址:https://arxiv.org/pdf/1412.5567.pdf

 

First-Pass Large VocabularyContinuous Speech Recognition using Bi-Directional Recurrent DNNs

PDF地址:https://arxiv.org/pdf/1408.2873.pdf

 

Grounded Compositional Semantics forFinding and Describing Images with Sentences

PDF地址:http://www.anthology.aclweb.org/Q/Q14/Q14-1017.pdf

 

Increasing Deep Neural NetworkAcoustic Model Size for Large Vocabulary Continuous Speech Recognition

PDF地址:https://core.ac.uk/download/pdf/25038772.pdf

 

Mechatronic design of an integratedrobotic hand

地址:http://journals.sagepub.com/doi/abs/10.1177/0278364913515032?journalCode=ijra(无PDF)

 

OfferingVerified Credentials in Massive Open Online Courses: MOOCs and technology toadvance learning and learning research (Ubiquity symposium)

PDF地址:http://ai.stanford.edu/~amaas/papers/amaas_mooc_verified.pdf

 

 

2013


Arrangement and method forthree-dimensional depth image construction

PDF地址:http://www.freepatentsonline.com/8472699.pdf

 

Deep learning for class-generic objectdetection

PDF地址:https://arxiv.org/pdf/1312.6885.pdf

 

Deep learning with COTS HPCsystems

PDF地址:http://web.stanford.edu/~dwu4/ICML2013.pdf

 

Learning New Facts From Knowledge Bases With NeuralTensor Networks and Semantic Word Vectors

PDF地址:https://arxiv.org/pdf/1301.3618.pdf

 

PEGASUS: A Policy SearchMethod for Large MDPs and POMDPs

pdf地址:http://people.eecs.berkeley.edu/~pabbeel/cs287-fa09/readings/NgJordan-Pegasus-UAI2000.pdf

 

Parsing with Compositional VectorGrammars

PDF地址:http://anthology.aclweb.org/P/P13/P13-1045.pdf

 

RECURRENT NEURAL NETWORK FEATURE ENHANCEMENT: THE 2ndCHIME CHALLENGE

PDF地址:http://stanford.edu/~awni/papers/drdae_chime2013_final.pdf

 

Rectifier Nonlinearities Improve Neural NetworkAcoustic Models

PDF地址:http://web.stanford.edu/~awni/papers/relu_hybrid_icml2013_final.pdf

 

Reasoning With Neural Tensor Networks forKnowledge Base Completion

PDF地址:http://cs.stanford.edu/people/danqi/papers/nips2013.pdf

 

Tuned Models of Peer Assessment inMOOCs

PDF地址:https://arxiv.org/pdf/1307.2579.pdf


The Online Revolution: Education forEveryone

PDF地址:https://cn.aminer.org/upload/pdf/1104/996/1346/5528fdda45cecbb322b368f3.pdf

 

Zero-Shot Learning ThroughCross-Modal Transfer

PDF地址:https://arxiv.org/pdf/1301.3666.pdf


整理:银月子爵

本文为机械鸡公众号原创文章,转载前请务必联系作者授权。


 推荐阅读

谷歌首席人工智能科学家李飞飞发表的史上最全论文合集(附下载)

重磅 ‖ 科学家通过读取猕猴的脑电波,来重构人脸(附代码+数据库+论文)

干货 ‖ 机器学习和深度学习工程师必须收藏的速查表

读完这21个机器学习面试问题和答案,入职率提升99%

25个深度学习初学者必须了解的术语


招聘「志愿者 」

希望你有稳定输出的时间,英文能力佳,从业者优先。

加入「AI从业者社群」请备注个人信息

添加小鸡微信 liulailiuwang