发布于 2017/09/10 01:22
字数 717
阅读 3
收藏 0
点赞 0
评论 0

  1. 【博客】100 Must-Read NLProc Papers


This is a list of 100 important natural language processing (NLP) papers that serious students and researchers working in the field should probably know about and read.

This list is originally based on the answers for a Quora question I posted years ago: What are the most important research papers which all NLP studnets should definitely read?. I thank all the people who contributed to the original post.

This list is far from complete or objective, and is evolving, as important papers are being published year after year. Please let me know via pull requests and issues if anything is missing.


2.【博客】Variational Inference with Implicit Models Part II: Amortised Inference


In a previous post I showed a simple way to use a GAN-style algorithm to perform approximate inference with implicit variational distributions. There, I used a Bayesian linear regression model where we aim to infer a single global hidden variable given a set of conditionally i.i.d. observations. In this post I will consider a slightly more complicated model with one latent variable per observation, and just like in variational autoencoders (VAEs), we are going to derive an amortised variational inference scheme.



3.【论文&代码】Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer


PyTorch 代码

Attention plays a critical role in human visual experience. Furthermore, it has
recently been demonstrated that attention can also play an important role in the context of applying artificial neural networks to a variety of tasks from fields such as computer vision and NLP. In this work we show that, by properly defining attention for convolutional neural networks, we can actually use this type of information in order to significantly improve the performance of a student CNN network by forcing it to mimic the attention maps of a powerful teacher network. To that end, we propose several novel methods of transferring attention, showing consistent improvement across a variety of datasets and convolutional neural network architectures.



4.【视频数据】A benchmark initiative for all things video


VideoNet is a new initiative to bring together the community of researchers that have put effort into creating benchmarks for video tasks. Our goal is to bring together video benchmarks, exchange ideas on how to improve annotations, evaluation measures, and learn from each other's experiences. Cameras are around us everywhere, generating millions of frames of video footage every day. Why limit yourself to a single image when you can have a video? Discover the challenges of video processing here.


5.【论文】The cornucopia of meaningful leads: Applying deep adversarial autoencoders for new molecule development in oncology


Recent advances in deep learning and specifically in generative adversarial networks have demonstrated surprising results in generating new images and videos upon request even using natural language as input. In this paper we present the first application of generative adversarial autoencoders (AAE) for generating novel molecular fingerprints with a defined set of parameters. We developed a 7-layer AAE architecture with the latent middle layer serving as a discriminator. As an input and output the AAE uses a vector of binary fingerprints and concentration of the molecule. In the latent layer we also introduced a neuron responsible for growth inhibition percentage, which when negative indicates the reduction in the number of tumor cells after the treatment. To train the AAE we used the NCI-60 cell line assay data for 6252 compounds profiled on MCF-7 cell line. The output of the AAE was used to screen 72 million compounds in PubChem and select candidate molecules with potential anti-cancer properties. This approach is a proof of concept of an artificially-intelligent drug discovery engine, where AAEs are used to generate new molecular fingerprints with the desired molecular properties.


© 著作权归作者所有

共有 人打赏支持
粉丝 10
博文 2139
码字总数 82983
作品 0
预测流行偏好,时尚 AI 未来可望取代造型师


黄 嬿 ⋅ 2017/12/26 ⋅ 0



人工智豪 ⋅ 2017/06/03 ⋅ 0


1.【会议】Bayesian Deep Learning 简介: While deep learning has been revolutionary for machine learning, most modern deep learning models cannot represent their uncertainty nor......

chen_h ⋅ 2017/12/03 ⋅ 0

Nature 新论文:让机器人像动物一样进化

雷锋网(公众号:雷锋网)按:这里是,雷锋字幕组编译的Two minutes paper专栏,每周带大家用碎片时间阅览前沿技术,了解AI领域的最新研究成果。 原标题 This Robot Adapts Like Animals 翻译 ...

雷锋字幕组 ⋅ 05/21 ⋅ 0



黄 斯沛 ⋅ 04/16 ⋅ 0



zhouzxi ⋅ 2017/07/15 ⋅ 0


人工智能的大脑 今天是12月3号星期天,明天就要重新开始上班,迎接新的一周。今天AI小编和大家一起来聊聊AI领域的芯片。 AI芯片人工智能时代的大脑,驱动人工智能时代进步的核心要素,目前国...

移动笔记 ⋅ 2017/12/03 ⋅ 0

王家林人工智能AI第19课:使用决策树在Social Network上构建汽车销售推荐系统老师微信13928463918

王家林人工智能AI第19课:使用决策树在Social Network上构建汽车销售推荐系统老师微信13928463918 决策树中的熵entropy: classifier = DecisionTreeClassifier(criterion = 'entropy', ran...

duan_zhihua ⋅ 05/12 ⋅ 0


有人说,要想知道人工智能有多火,看专利数量就知道了。据统计,全球 AI 相关领域的专利总数已超过 13 万份,我国AI专利数量也迎来了超速增长。韩媒报道称我国AI专利数量是他们的5.5倍,但更...

gusii ⋅ 06/14 ⋅ 0

首期腾讯AI加速器毕业 9个月项目总估值翻3倍


机器之心 ⋅ 04/13 ⋅ 0






摘要: 目前云效上线了企业级Maven私有仓库服务。用户可以一键开通Maven私有仓库服务,零配置实现私有二方库的上传和下载。 经过半个月的公测,云效中的企业级Maven私有仓库服务正式上线,全...

阿里云云栖社区 ⋅ 12分钟前 ⋅ 0


官网地址:https://www.elastic.co/guide/en/elasticsearch/reference/2.3/query-dsl-mlt-query.html 基于内容的推荐通常是给定一篇文档信息,然后给用户推荐与该文档相识的文档。Lucene的a...

xiaomin0322 ⋅ 15分钟前 ⋅ 0

Spring Boot更改Banner

Spring Boot 1.0 中如何更换启动 Banner,其实都很简单,只需要在src/main/resources路径下新建一个banner.txt文件,banner.txt中填写好需要打印的字符串内容即可。 一般情况下,我们会借助第...

Clarence_D ⋅ 19分钟前 ⋅ 0


谷歌浏览器在记住密码后,在input获取焦点的时候就会有输入提示框,如: 有时候我们在输入用户名时,我们自己有ajax的下拉展示列表,那么此时的历史提示输入框就影响交互和用户体检,解决的方...

莫西摩西 ⋅ 21分钟前 ⋅ 0


简介 DLNA的全称是DIGITAL LIVING NETWORK ALLIANCE(数字生活网络联盟), 其宗旨是Enjoy your music, photos and videos, anywhere anytime, DLNA(Digital Living Network Alliance) 由索尼......

啊哼哼 ⋅ 27分钟前 ⋅ 0


  Python IDE工具是每个Python工程师必须使用的开发工具,选择正确的编辑器对Python编程效率的影响是非常大的,因此选择合适的Python开发工具十分重要,以下是通过长期实践发掘的好用的Pyt...

老男孩Linux培训 ⋅ 28分钟前 ⋅ 0

happybase(TSocket read 0 bytes)

关于报错 happybase 是使用python连接hbase的一个第三方库,目前基于thrift1 。在使用过程中经常碰到报错 TTransportException(type=4, message='TSocket read 0 bytes') 即使使用thrift se...

zhnxin ⋅ 29分钟前 ⋅ 0


1. 获取接口对应的实现类 package com.rpc.server.util; import java.io.File; import java.net.URL; import com.alibaba.fastjson.JSON; public class ClassUtils { public static Object ......

徐志 ⋅ 29分钟前 ⋅ 0


四、服务器的gzip压缩 1.ngx_http_gzip_module模块处理的9个指令 在处理时实时压缩 1>gzip on|off 开启或关闭gzip功能 2>gzip_buffers number size 用于设置文件使用缓存...

余温灬未存 ⋅ 31分钟前 ⋅ 0

前端程序员:月薪 5K 到 5 万,我干了啥

高贵的前端程序猿们: 如何在前端开发这种高精尖的技术领域找到心仪的工作?实现在咖啡馆喝喝咖啡敲敲代码就能升职加薪、买房买车、迎娶白富美走上人生巅峰的职业梦想?这 篇《进化论:从 0 ...

Mr_zebra ⋅ 33分钟前 ⋅ 0