Artificial Intelligence News — Newsletter on Deep Learning & AI – Artificial Intelligence News #81

IN THE NEWS

  • Microsoft asks the U.S. Congress to regulate face recognition. More
  • A report by the Australian Strategic Policy Institute urges better oversight of international partnerships on AI, to ensure that collaborations are not being exploited for military uses. More
  • Facebook hires head of chip development from Google. More

LEARNING



SOFTWARE TOOLS & CODE



WORKPLACE

Hiring? Looking for a job?

I am listing open positions in A.I. / M.L. here. Feel free to submit open positions here!

SOME INSPIRATION

Artificial Intelligence News — Newsletter on Deep Learning & AI – Artificial Intelligence News #80

WELCOME

Are you hiring?

I will soon start listing open positions in the newsletter, and I’d be happy to include your job listing in AIWeekly for free. (just so you know, AIWeekly currently has ~14000 subscribers)

Fill out this form to add an open position to the job board. Thank you!

IN THE NEWS



LEARNING




SOFTWARE TOOLS & CODE



Deep Learning Weekly – 🤖 – Issue #87: AI Principles, 12TB RAM, AI Bubble, Tiny Devices, Software Stack 2.0, One-Shot Object Detection, Create ML and more… | Revue

 

Hey Folks! This week, we learn about Google’s AI principles, Microsoft announced machines with huge a
 
June 14 · Issue #87 · View online
Deep Learning Weekly

Hey Folks!
This week, we learn about Google’s AI principles, Microsoft announced machines with huge amounts of memory, first thoughts about an AI bubble begin to surface and we take a look at machine learning on tiny devices.
Andrej Karpathy shares some interesting views on the software stack 2.0 at Tesla, we learn everything about one-shot object detection and AutoAugment from Google, take a look at Apples new Create ML tool and get to know a machine learning toolchain built for artists.
As we just crossed 8000 subscribers, we would like to thank you once again for all of your support. As always, if you want to help us grow this great community of deep learning enthusiasts, simply share this issue with friends and colleagues.
See you next week!


Industry

AI at Google: our principles


Microsoft Azure will soon offer machines with up to 12 TB of memory


When the bubble bursts…


Why the Future of Machine Learning is Tiny

Why This Startup Created A Deep Learning Chip For Autonomous Vehicles

Sponsored Link

Mention DLWEEKLY for $400 USD discount on any Lambda Quad!
Learning

Building the Software 2.0 Stack by Andrej Karpathy from Tesla


One-shot object detection


Improving Deep Learning Performance with AutoAugment

Libraries & Code

Training a Text Classifier with Create ML and the Natural Language Framework

LSTM · ml5js

Papers & Publications

Improving Language Understanding with Unsupervised Learning

Why do deep convolutional networks generalize so poorly to small image transformations?

Did you enjoy this issue?


If you don’t want these updates anymore, please unsubscribe here
If you were forwarded this newsletter and you like it, you can subscribe here
Powered by Revue
 

 

Deep Learning Weekly – 🤖 – Issue #88: OpenAI Five, Twitter Workflows, Speech Synthesis, Inverse RL, DensePose, Confusing TensorFlow and more… | Revue

 

Hey and welcome to another week in deep learning! This week, we obviously start off with OpenAIs move
 
June 27 · Issue #88 · View online
Deep Learning Weekly

Hey and welcome to another week in deep learning!
This week, we obviously start off with OpenAIs move into Dota 2 gaming, look at ML Workflows at Twitter, learn about reduced GPU pricing on GCP and explore speech synthesis services as well as depth inference for photo editing. We learn about inverse reinforcement learning, object detection, and photo caption. Afterward, we get a great TensorFlow concepts explanation from a Google Brain resident, get to know Facebooks DensePose, a new portal linking papers and code, and the best paper of CVPR2018.
As always, we hope you’ll enjoy reading as much as we did and would appreciate you sharing this newsletter with friends and colleagues.
You may have noticed, that we’re currently running on a bi-weekly schedule due to various reasons, but hope to bring the newsletter back to the normal pace soon. To make up for the delays, we just added a few more links to this weeks issue.
Happy reading and hacking!


Industry

OpenAI Five


Productionizing ML with Workflows at Twitter


Introducing improved pricing for Preemptible GPUs


Speech Synthesis as a Service


From 2D to 3D Photo Editing

Learning

Learning from humans: what is inverse reinforcement learning?


Understanding Deep Learning for Object Detection


How to Develop a Deep Learning Photo Caption Generator from Scratch

Libraries & Code
Tensorflow: The Confusing Parts


Introducing Apex: PyTorch Extension with Tools to Realize the Power of Tensor Cores


Facebook open sources DensePose


NLP-progress: Repository to track the progress in Natural Language Processing (NLP)

Papers & Publications
Papers with Code: The latest in machine learning

Taskonomy: Disentangling Task Transfer Learning

On Calibration of Modern Neural Networks

Did you enjoy this issue?


If you don’t want these updates anymore, please unsubscribe here
If you were forwarded this newsletter and you like it, you can subscribe here
Powered by Revue
 

 

Deep Learning Weekly – Issue #90 – 🤖- Troubling Trends in Machine Learning Research, Design Patterns for Production NLP System & Improving Connectomics | Revue

 

Howdy folks and welcome to another week in deep learning! This week we take a look at the ominous use
 
July 19 · Issue #90 · View online
Deep Learning Weekly

Howdy folks and welcome to another week in deep learning!
This week we take a look at the ominous uses of AI by the Chinese government, some troubling trends in machine learning research, we learn about feature wise transforms and design patterns for production NLP systems
A fun little bit of trivia, the whimsical Not Hotdog App known from the HBO show Silicon Valley was built by fast.ai student and is now nominated for an Emmy.
Happy reading and hacking!


Industry

An Overview of National AI Strategies – Politics + AI


Inside China’s Dystopian Dreams: A.I., Shame and Lots of Cameras


Apple’s New AI Chief Takes on Oversight of Siri

Facebook AI Research Expands With New Academic Collaborations

Troubling Trends in Machine Learning Scholarship

Sponsored Link

Deep Learning Weekly has secured a £200 discount off registration, quote DLW200!
Learning

Design Patterns for Production NLP Systems


Feature-wise Transformations


Using Deep Learning to Automatically Rank Millions of Hotel Images

Libraries & Code

Switchable-Normalization


A Project Based Introduction to TensorFlow.js – Knowledge-Exploration Systems

Papers & Publications
Google AI Blog: Improving Connectomics by an Order of Magnitude


Glow: Better Reversible Generative Models


Proceedings of Machine Learning Research

An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution

Did you enjoy this issue?


If you don’t want these updates anymore, please unsubscribe here
If you were forwarded this newsletter and you like it, you can subscribe here
Powered by Revue
 

 

爱可可老师24小时热门分享(2018.7.30)

No 1. 《Python深度学习》
No 2. 《如何从一个空有上进心的人,变成行动上的巨人? – 知乎》
No 3. '中华新华字典数据库。包括歇后语,成语,汉字。提供新华字典API' by PWXCOO GitHub…
No 4. 重要的是,不要固步自封 – 别怕犯错,别怕看上去有多蠢,别在意那些取笑你、想羞辱你的人。探索、实践、…
No 5. 【PyTorch深度学习迷你教程】
No 6. 【把命令行操作过程录制成gif】
No 7. 【Keras实现的Image OutPainting:用GAN绘制“画框外”的世界】
No 8. 所谓神似…… ​
No 9. 《是否真的存在天才? – 知乎》
No 10. 【对大量pdf文档模糊搜索的命令行工具】
No 11. 中国留学生回国率:1987年:5% 2007年:30% 2017年:79%src:http:…
No 12. 【今日限免:Python软件架构与设计】
No 13. “Best Comment”
No 14. 《Research Question: Little Quick Fix》
No 15. 【新书:TensorFlow预测分析】
No 16. 《Practical Guide to Bare Metal C++》
No 17. 《Bandit Algorithms》
No 18. 《Clinical Text Classification with Rule-based Features and Knowledge-guided Convolutional Neural Networks》
No 19. 【基于TensorFlow.js的张量计算(可微线代)试炼场(Web)】
No 20. 牛仔裤加工已经这么先进了? http://t.cn/Re6MLDF ​…
No 21. 《智能运维:从0搭建大规模分布式AIOps系统》
No 22. 无始无终(用单面镜、LED、钢铁制成) by Anthony James src:
No 23. 【用绵羊来解释熵——从融化的冰块到时间之谜】
No 24. 机器学习的每一波“浪潮”
No 25. 回顾:追踪NLP最新技术进展的两个好地方:NLP-progress http://t.cn/Rgk6…
No 26. 《The Hitchhiker's Guide to Tensorflow – Introduction to Machine Learning and Tensorflow – YouTube》
No 27. 《Learning the effect of latent variables in Gaussian Graphical models with unobserved variables》
No 28. 《Distributed Second-order Convex Optimization》
No 29. 《Deep Sequential Multi-camera Feature Fusion for Person Re-identification》
No 30. 该来的总会来:AR甲油试妆App——最流行的,永远不必是技术上最难的 ​​​…
No 31. 《General Value Function Networks》
No 32. 《Recurrent Capsule Network for Relations Extraction: A Practical Application to the Severity Classification of Coronary Artery Disease》
No 33. 《Decision Variance in Online Learning》
No 34. 《Cyclostationary Statistical Models and Algorithms for Anomaly Detection Using Multi-Modal Data》
No 35. 四大生成模型优缺点比较:Autoregressive, VAE, Normalized, and G…
No 36. 【自然语言处理好好玩】
No 37. 《爱可可老师24小时热门分享(2018.7.29)》
No 38. 《Iterative Amortized Inference》
No 39. 【PyTorch指南:使用、思考、技巧与陷阱】
No 40. “神似”
No 41. 【CT扫描数据集】
No 42. 【文本分类数据准备/模型选择流程图】
No 43. 《Multimodal Social Media Analysis for Gang Violence Prevention》
No 44. 欢迎参与!
No 45. 【超智AI的谬误与事实】
No 46. 物理老师伯恩斯先生制作的双黑洞发射#引力波#可视化 http://t.cn/RdPNH3e ​…
No 47. 【Kaggle比赛实战教程(Pandas, Matplotlib, XGBoost/Colab)】
No 48. 替朋友们专门查了下,此App叫“WANNA NAILS”
No 49. 【Kaggle出品的小型数据科学系列课程】
No 50. 《Automatically Designing CNN Architectures for Medical Image Segmentation》

爱可可老师24小时热门分享(2018.7.29)

No 1. 《Python深度学习》
No 2. 回顾:追踪NLP最新技术进展的两个好地方:NLP-progress http://t.cn/Rgk6…
No 3. 机器学习的每一波“浪潮”
No 4. 无始无终(用单面镜、LED、钢铁制成) by Anthony James src:
No 5. [笑cry] ​
No 6. 四大生成模型优缺点比较:Autoregressive, VAE, Normalized, and G…
No 7. 该来的总会来:AR甲油试妆App——最流行的,永远不必是技术上最难的 ​​​…
No 8. 中国留学生回国率:1987年:5% 2007年:30% 2017年:79%src:http:…
No 9. 【CT扫描数据集】
No 10. 牛仔裤加工已经这么先进了? http://t.cn/Re6MLDF ​…
No 11. “Best Comment”
No 12. 学术圈最棒的一点是自己可以当自己的老板,最糟糕的一点是我老板是个笨蛋。
No 13. 不论是入门难度、可移植性、开放资源丰富程度、社区成熟度,还是在AI领域的使用热门程度,Python应…
No 14. 《智能运维:从0搭建大规模分布式AIOps系统》
No 15. “神似”
No 16. 《Multi-Agent Reinforcement Learning: A Report on Challenges and Approaches》
No 17. “The Markov-chain Monte Carlo Interactive Gallery”
No 18. 【Kaggle比赛实战教程(Pandas, Matplotlib, XGBoost/Colab)】
No 19. 步进视错觉 ​
No 20. 【在自字符界面绘制图表的命令行工具】
No 21. 《The Hitchhiker's Guide to Tensorflow – Introduction to Machine Learning and Tensorflow – YouTube》
No 22. 记住:科学的目的是产生知识,而非公关(PR)。应该根据是否能回答某些开放的科学问题,来选择研究项目—…
No 23. 替朋友们专门查了下,此App叫“WANNA NAILS”
No 24. 《Automatically Designing CNN Architectures for Medical Image Segmentation》
No 25. 精彩创意:360° Book http://t.cn/Rex1YDA ​
No 26. 【PyTorch指南:使用、思考、技巧与陷阱】
No 27. 【用绵羊来解释熵——从融化的冰块到时间之谜】
No 28. 《Meta-Learning Priors for Efficient Online Bayesian Regression》
No 29. 《Deep Supervision with Intermediate Concepts》
No 30. 起跑线~ ​
No 31. 《Hierarchical Classification using Binary Data》
No 32. 《2018自然语言处理研究报告》
No 33. 《The “TerpreT problem” and the limits of SGD》
No 34. 【Facebook出品的视觉问答(VQA)系统】
No 35. 《Differentiable Learning-to-Normalize via Switchable Normalization》
No 36. 《DARTS: Differentiable Architecture Search》
No 37. 准确的说,是审美潜变量约束泛化[嘻嘻] http://t.cn/ReMDDKL //@爱可可-爱生…
No 38. 《Understanding and representing the semantics of large structured documents》
No 39. 《爱可可老师24小时热门分享(2018.7.28)》
No 40. 《Discrete linear-complexity reinforcement learning in continuous action spaces for Q-learning algorithms》
No 41. 《Where are the Blobs: Counting by Localization with Point Supervision》
No 42. 转发微博
No 43. 欢迎参与!
No 44. 【recurrent sequence models vs. feedforward models】
No 45. Switchable Normalization for object detection GitH…
No 46. “Kaggle比赛实战教程”
No 47. 《UNet++: A Nested U-Net Architecture for Medical Image Segmentation》
No 48. “ICML 2018 Workshop on Deep Generative Models – Invited Speakers(Slides)”
No 49. 【如何选择论文投稿的期刊?】
No 50. 《Generating a Fusion Image: One's Identity and Another's Shape》

爱可可老师24小时热门分享(2018.7.28)

No 1. 《Python深度学习》
No 2. “神似”
No 3. 【Kaggle比赛实战教程(Pandas, Matplotlib, XGBoost/Colab)】
No 4. 起跑线~ ​
No 5. 【PyTorch指南:使用、思考、技巧与陷阱】
No 6. 不管是程序员面试,还是大作业,“不许用Google搜索或不许翻书”
No 7. 回顾:追踪NLP最新技术进展的两个好地方:NLP-progress http://t.cn/Rgk6…
No 8. 成长: 保持好奇 – 真正理解之前别轻易忽略任何一个想法;不要满足于自以为所了解的 保持批评…
No 9. 《智能运维:从0搭建大规模分布式AIOps系统》
No 10. 简单有趣的十秒动画可视化证明
No 11. 四大生成模型优缺点比较:Autoregressive, VAE, Normalized, and G…
No 12. 【如何选择论文投稿的期刊?】
No 13. 人类泛化能力遥遥领先
No 14. 【迁移学习自然语言处理】
No 15. 《UNet++: A Nested U-Net Architecture for Medical Image Segmentation》
No 16. 【Facebook出品的视觉问答(VQA)系统】
No 17. 《2018自然语言处理研究报告》
No 18. 《Generating a Fusion Image: One's Identity and Another's Shape》
No 19. 【深度学习应用实例集】
No 20. “Kaggle比赛实战教程”
No 21. 什么最贵?精度?还是时间?
No 22. 转发微博
No 23. 【recurrent sequence models vs. feedforward models】
No 24. 【CT扫描数据集】
No 25. 准确的说,是审美潜变量约束泛化[嘻嘻] http://t.cn/ReMDDKL //@爱可可-爱生…
No 26. 【打造像人一样学习和思考的机器】
No 27. 专业技巧:忽略之前所有工作,你的任何研究都将是新颖的
No 28. 《GANimation: Anatomically-aware Facial Animation from a Single Image》
No 29. “ICML 2018 Workshop on Deep Generative Models – Invited Speakers(Slides)”
No 30. 【AI机器翻译超过人类了吗?恐怕还远得很!】
No 31. 玩星际争霸,#DotA#或Overwatch的AI能否打赢顶级人类选手,从结果或许得不出任何结论…
No 32. 《Meta-learning autoencoders for few-shot prediction》
No 33. 【深度学习与免费软件:神经网络权重是否该免费?】
No 34. 步进视错觉 ​
No 35. 看到广告说“要像TED演讲一样对待每次报告”
No 36. 《LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks》
No 37. 【隐式依赖捕获】
No 38. 【解耦表示学习文献集】
No 39. 【图解ps命令】
No 40. 《Variational Memory Encoder-Decoder》
No 41. 《Multi-Agent Generative Adversarial Imitation Learning》
No 42. 精彩创意:360° Book http://t.cn/Rex1YDA ​
No 43. “The Markov-chain Monte Carlo Interactive Gallery”
No 44. 【在自字符界面绘制图表的命令行工具】
No 45. 【无需博士学位的TensorFlow教程:深度学习与CNN】
No 46. 《Social Connection Induces Cultural Contraction: Evidence from Hyperbolic Embeddings of Social and Semantic Networks》
No 47. 【多任务学习的新研究】
No 48. 【在ACLU对名为“Rekognition”的面部识别工具的测试中,该软件错误地对28名国会议员进行了匹配,将他们识别为因犯罪而被捕的其他人】
No 49. 【面向科学家的Python编程指南】
No 50. 【自然语言处理好好玩】

MongoDB发布4.0版本;GitHub重构页面移除了jQuery – InfoQ每周精要547期

 中文站「每周精要」
感谢您订阅每周精要第 547 期,本期内容截止于2018-07-29。
技术新闻   TECH NEWS
MongoDB发布4.0版本,支持ACID事务
MongoDB最近发布了最新的4.0版本。
改名之后的Java EE,现在有什么新进展?
这篇文章中,Cesar Saavedra将解释为什么说Jakarta EE为企业版Java带来了新鲜的空气。
GitHub推出Python安全警告
GitHub宣布了Python安全警告,使Python用户可以访问依赖图,并在他们的库所依赖的包存在安全漏洞时收到警告。
微软发布Azure Service Fabric Mesh公开预览版
Service Fabric现在在云端有了一个新亲戚——Azure Service Fabric Mesh,Azure的一个完全托管服务,开发人员现在可以基于此服务部署和运行容器化应用程序。
Kotlin生态调查结果出炉:超过6成的开发者用过Kotlin了
来自Stack Overflow的一项问卷调查显示,超过10万名受调者表示Kotlin是他们的第二大编程语言。
Netflix发布Polly.JS,一个用于HTTP交互的开源库
Netflix最近发布了Polly.JS,一个用于记录、重放和模拟HTTP交互的开源库。
架构设计   ARCHITECTURE DESIGN
为什么能有上百万个Goroutines,却只能有上千个Java线程?
Jakarta EE正在为企业版Java开辟新的道路。在这篇文章中,Cesar Saavedra将解释为什么说Jakarta EE为企业版Java带来了新鲜的空气。
微服务接口限流的设计与思考(附GitHub框架源码)
服务治理本身的概念比较大,包括鉴权、限流、降级、熔断、监控告警等等,本文聚焦于限流,根据笔者的实战经验,分享一些对微服务接口限流的思考。
治大国若烹小鲜,大规模Kubernetes集群的运营哲学
有些人会说,Kubernetes已经这么成熟了,都是开源的,而且已经有这么多的工具进行部署监控了,集群的运维会有什么难度。其实不然。
运维 & DevOps   OPERATIONS & DEVOPS
Go Cloud项目开源发布:Go语言将成为云端应用开发的首选语言?
Go 语言团队发布了一个新的开源项目 Go Cloud,用于开发具有可移植性的云端应用程序。
来自谷歌团队的容器运维最佳实践
谷歌大神们带你进行容器运维最佳实践。
想要高效上传下载?试试去中心化的Docker镜像仓库设计思路
在跨国上传下载的场景下,Docker Registry存在性能瓶颈,高网络延迟导致用户pull下载消耗更长的时间,同时集中式服务遭黑客的DDos攻击会面临瘫痪。
大前端   THE FRONT END
GitHub重构页面移除了jQuery
喜欢的开源的同学肯定会注意到最近GitHub的改版,不知道大家是否习惯新的Dashboard呢?
谷歌为什么要对Android的开源严防死守?
从这些年Google的对Android的态度来看,他们正以各种手段控制开源,这与Android开放的口号是否相悖?Google又为何这样做?
如何在Node.js中优化服务器端渲染?
Airbnb通过Node.js提供完整的服务器端渲染页面,这个服务为所有产品渲染大部分HTML。
人工智能   ARTIFICIAL INTELLIGENCE
Spark比拼Flink:下一代大数据计算引擎之争,谁主沉浮?
Spark和Flink大比拼,你Pick谁?
谷歌BigQuery ML正式上岗,只会用SQL也能玩转机器学习!
谷歌黑科技!真·别动不动就机器学习,SQL就够用了!
AI一周热闻:百度杰出科学家徐伟离职加盟地平线;阿里投资旷视科技超6亿美元
有人损了大将,有人拿到了融资,本周AI圈依然是几家欢喜几家愁。
区块链   BLOCKCHAIN
操作有毒!90后少年搭了一条区块链后,开始教别人怎样复制
程序员的天赋技能就是通过代码实践自己的想法,完成一个作品会有相当的成就感,所以今天我们以 C++14 的代码为例子,和你分享设计并实现一个迷你区块链例子。
百度超级链首个应用图腾落地,跨界公链+AI+大数据
7月18日,百度正式宣布推出基于区块链技术的原创图片服务平台“图腾”,这也是基于百度超级链开发的首个区块链的应用。
区块链杀手级应用形式:颠覆价值数万亿美元的庞大产业,改变企业发展格局
供应链行业在全球范围内的年均GDP达到54万亿美元,因此即使对其作出小幅改善,也足以给全球的财富创造体系产生重大影响。
技术大会   CONFERENCE
QCon:从0到3000万用户,微服务架构该怎么升级
把单一应用程序划分成一组组的服务,服务之间互相协调、互相配合,对于提高研发团队间的并行化研发速度,提升开发效率、提高模块复用性有很大作用,也为用户提供了更多价值。 ​​​​
CNUTCon:自动化运维平台实践
随着运维管理的复杂度和难度增大,资源和流程的标准化统一化、应用运行状态可视化管理越来越重要,11月的CNUTCon上将分享主流公司工具自动化向一站式自动化运维管理平台演化的经验。
AICon:《西部世界》里的世界,就在看得见的未来?
2018年,AI定义万物,人工智能上升为国家战略,我们真的要迎来一个与机器对话的时代了。InfoQ中国特别策划AICon全球人工智能与机器学习技术大会,邀请国内外顶尖AI技术公司和人工智能专家来聊一聊目前最新最火的AI实践案例。
极客时间App   GEEK TIME APP
程序员,该如何提升自己编码之外的能力?
作为程序员,该如何提升自己的产品思维和商业意识?让程序员出身,7个月把「抽奖助手」用户量从0做到了2000万的邱岳,带给你他的分享。
技术人如何修炼金字塔型的自我成长?
作为技术人最重要到就是不断学习,不应沉浸于单一技术提升,这是每个技术人在技能提升道路上必须面临的挑战。推荐下极客时间的VIP年卡服务,据说有30多个国内外一线技术leader分享自己的开发经验和实例,一定对你的技术进阶有帮助。
技术领导力300讲,每个技术领导者都应该知道的管理心经
100 位身经百战的技术管理者们,基于实践经验的总结和提炼你一定要看。
活动推荐   POPULAR EVENTS
机器学习在无人驾驶、WebRTC等领域的应用
WebRTC怎么与无人驾驶结合?机器学习能为编解码调优百分之几?机器学习怎么优化QoE?RTC 2018实时互联网大会为你逐一解答。
众星云集,决战AI之巅
2018百度之星大赛荣耀登场!融入无限智慧与现代科技的真正较量,让AI技术爱好者迸发出无限可能!来这里,开启你我的黄金时代!千万不要错过!
推动视频云领域核心突破,它一直“在路上”
随着全民视频时代的到来,如何更好的借助AI技术并保证内容实时传输?迎难而上!七牛云手握五大关键要素助力你一路“破关斩将”。
InfoQ中文站每周日针对会员发送每周内容精要邮件,
别人转发给你的邮件?现在注册获取您自己的 InfoQ每周精要邮件吧
InfoQ微博:@InfoQ
InfoQ微信:infoqchina
InfoQ手机客户端:极客时间

爱可可老师一周论文精选(2018.7.28)

No 1. 【用GAN给裸女自动“穿”上比基尼
No 2. 【Rosetta:大规模图像文字检测识别系统】
No 3. 《Detecting Visual Relationships Using Box Attention》
No 4. 【全局上下文场景图解析】
No 5. 《Recent Advances in Deep Learning: An Overview》
No 6. 《Deep Clustering for Unsupervised Learning of Visual Features》
No 7. 【单图像去雨(PyTorch)】
No 8. 《Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizer》
No 9. 《Manifold Adversarial Learning》
No 10. 《Deep Learning》
No 11. 《Learning to Segment Medical Images with Scribble-Supervision Alone》
No 12. 《Compositional GAN: Learning Conditional Image Composition》
No 13. 【将Tensorflow中编写的数值计算模型映射到FPGA合成设计的开源工具】
No 14. 《ClusterNet: Instance Segmentation in RGB-D Images》
No 15. 《Deep Learning for Semantic Segmentation on Minimal Hardware》
No 16. 《Physical Adversarial Examples for Object Detectors》
No 17. 《TextTopicNet – Self-Supervised Learning of Visual Features Through Embedding Images on Semantic Text Spaces》
No 18. 《Neural Networks Regularization Through Representation Learning》
No 19. 《The Variational Homoencoder: Learning to learn high capacity generative models from few examples》
No 20. 《Generalization Bounds for Unsupervised Cross-Domain Mapping with WGANs》
No 21. 《From Face Recognition to Models of Identity: A Bayesian Approach to Learning about Unknown Identities from Unsupervised Data》
No 22. 《Eyeriss v2: A Flexible and High-Performance Accelerator for Emerging Deep Neural Networks》
No 23. 《A Generic Approach to Lung Field Segmentation from Chest Radiographs using Deep Space and Shape Learning》
No 24. 《Deep Transfer Learning for Cross-domain Activity Recognition》
No 25. 【打游戏进化算法表现超过深度学习】
No 26. 《Singular Value Decomposition of Operators on Reproducing Kernel Hilbert Spaces》
No 27. 《Variational Bayesian Reinforcement Learning with Regret Bounds》
No 28. 《VTA: An Open Hardware-Software Stack for Deep Learning》
No 29. 《3D Hand Pose Estimation using Simulation and Partial-Supervision with a Shared Latent Space》
No 30. 《Homology-Preserving Dimensionality Reduction via Manifold Landmarking and Tearing》