文档章节

人工智能资料库:第13辑(20170122)

AllenOR灵感
 AllenOR灵感
发布于 2017/09/10 01:22
字数 717
阅读 4
收藏 0

  1. 【博客】100 Must-Read NLProc Papers

简介:

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.

原文链接:https://github.com/mhagiwara/100-nlp-papers


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

简介:

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.

原文链接:

http://www.inference.vc/variational-inference-with-implicit-models-part-ii-amortised-inference-2/


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

简介:

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.

原文链接:https://arxiv.org/pdf/1612.03928v1.pdf

代码链接:https://github.com/szagoruyko/attention-transfer


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

简介:

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.

原文链接:http://videonet.team/


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

简介:


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.

原文链接:http://www.impactjournals.com/oncotarget/index.php?journal=oncotarget&page=article&op=view&path%5B0%5D=14073&path%5B1%5D=44886


本文转载自:http://www.jianshu.com/p/3a2f3f88aa3e

共有 人打赏支持
AllenOR灵感
粉丝 10
博文 2634
码字总数 82983
作品 0
程序员
预测流行偏好,时尚 AI 未来可望取代造型师

【Technews科技新报】预测时尚潮流是一项需要天分的工作,还得仰赖一个庞大的系统让少数人追捧的时尚进入大众流行市场,进而让业者赚取大笔钞票。现在预测工作也可以交给人工智能,让服饰业者...

黄 嬿
2017/12/26
0
0
人工智能资料库:第72辑(20171203)

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
0
人工智能知识整理-第1辑(20170603)-机器学习入门资源汇总

有一天我忽然忘记了一个函数的用法,于是就上谷歌搜,结果搜出来的竟然是自己写的一篇笔记,上面有很详细的回答。当时感觉是跟另外一个自己进行交流,那一个是刚学完知识,印象还非常深的自己...

人工智豪
2017/06/03
0
0
Nature 新论文:让机器人像动物一样进化

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 | Binpluto 整理 ...

雷锋字幕组
05/21
0
0
人工智能时代的工作、学习和生活---《人工智能》阅读笔记

自从“罗辑思维”栏目从优酷网站搬到得到APP并且变为每天几分钟的节目之后,我就很少收听它了。某天,我打开得到APP,并且点开了“罗辑思维”的节目清单,发现有一期的标题包含了“人工智能”...

zhouzxi
2017/07/15
0
0

没有更多内容

加载失败,请刷新页面

加载更多

你为什么在Redis里读到了本应过期的数据

一个事故的故事 晚上睡的正香突然被电话吵醒,对面是开发焦急的声音:我们的程序在访问redis的时候读到了本应过期的key导致整个业务逻辑出了问题,需要马上解决。 看到这里你可能会想:这是不...

IT--小哥
今天
2
0
祝大家节日快乐,阖家幸福! centos GnuTLS 漏洞

yum update -y gnutls 修复了GnuTLS 漏洞。更新到最新 gnutls.x86_64 0:2.12.23-22.el6 版本

yizhichao
昨天
5
0
Scrapy 1.5.0之选择器

构造选择器 Scrapy选择器是通过文本(Text)或 TextResponse 对象构造的 Selector 类的实例。 它根据输入类型自动选择最佳的解析规则(XML vs HTML): >>> from scrapy.selector import Sele...

Eappo_Geng
昨天
4
0
Windows下Git多账号配置,同一电脑多个ssh-key的管理

Windows下Git多账号配置,同一电脑多个ssh-key的管理   这一篇文章是对上一篇文章《Git-TortoiseGit完整配置流程》的拓展,所以需要对上一篇文章有所了解,当然直接往下看也可以,其中也有...

morpheusWB
昨天
5
0
中秋快乐!!!

HiBlock
昨天
3
0

没有更多内容

加载失败,请刷新页面

加载更多

返回顶部
顶部