文档章节

人工智能资料库:第65辑(20170805)

AllenOR灵感
 AllenOR灵感
发布于 2017/09/10 01:21
字数 741
阅读 1
收藏 0

1.【Quora】Rank the most important factors during a PhD, which will increase your probability of finding a good faculty position?

简介:

A2A: I’s hard to make a simple rank-ordered list here because these factors combine in complicated, non-linear ways. So let me just say what we end up discussing in our faculty-hiring process in various departments in CMU SCS. Perhaps that will give you some idea about what you should work on.

原文链接:https://www.quora.com/Rank-the-most-important-factors-during-a-PhD-which-will-increase-your-probability-of-finding-a-good-faculty-position/answer/Scott-E-Fahlman?ref=fb_page


2.【博客】Faces recreated from monkey brain signals

简介:


The brains of primates can resolve different faces with remarkable speed and reliability, but the underlying mechanisms are not fully understood.

The researchers showed pictures of human faces to macaques and then recorded patterns of brain activity.

The work could inspire new facial recognition algorithms, they report.
In earlier investigations, Professor Doris Tsao from the California Institute of Technology (Caltech) and colleagues had used functional magnetic resonance imaging (fMRI) in humans and other primates to work out which areas of the brain were responsible for identifying faces.

Six areas were found to be involved, all of which are located in part of the brain known as the inferior temporal (IT) cortex. The researchers described these six areas as "face patches".

原文链接:http://www.bbc.com/news/science-environment-40131242


3.【论文】A Fast Unified Model for Parsing and Sentence Understanding

简介:

Tree-structured neural networks exploit valuable syntactic parse information as they interpret the meanings of sentences. However, they suffer from two
key technical problems that make them slow and unwieldy for large-scale NLP tasks: they usually operate on parsed sentences and they do not directly support batched computation. We address these issues by introducing the Stackaugmented Parser-Interpreter Neural Network (SPINN), which combines parsing and interpretation within a single treesequence hybrid model by integrating treestructured sentence interpretation into the
linear sequential structure of a shift-reduce parser. Our model supports batched computation for a speedup of up to 25× over other tree-structured models, and its integrated parser can operate on unparsed data with little loss in accuracy. We evaluate it on the Stanford NLI entailment task and show that it significantly outperforms other sentence-encoding models.

原文链接:https://arxiv.org/pdf/1603.06021.pdf


4.【博客】Hierarchical Softmax

简介:

Hierarchical softmax is an alternative to the softmax in which the probability of any one outcome depends on a number of model parameters that is only logarithmic in the total number of outcomes. In “vanilla” softmax, on the other hand, the number of such parameters is linear in the number of total number of outcomes. In a case where there are many outcomes (e.g. in language modelling) this can be a huge difference. The consequence is that models using hierarchical softmax are significantly faster to train with stochastic gradient descent, since only the parameters upon which the current training example depend need to be updated, and less updates means we can move on to the next training example sooner. At evaluation time, hierarchical softmax models allow faster calculation of individual outcomes, again because they depend on less parameters (and because the calculation using the parameters is just as straightforward as in the softmax case). So hierarchical softmax is very interesting from a computational point-of-view. By explaining it here, I hope to convince you that it is also interesting conceptually. To keep things concrete, I’ll illustrate using the CBOW learning task from word2vec (and fasttext, and others).

原文链接:http://building-babylon.net/2017/08/01/hierarchical-softmax/


5.【博客】How to Visualize Your Recurrent Neural Network with Attention in Keras

简介:


Neural networks are taking over every part of our lives. In particular — thanks to deep learning — Siri can fetch you a taxi using your voice; and Google can enhance and organize your photos automagically. Here at Datalogue, we use deep learning to structurally and semantically understand data, allowing us to prepare it for use automatically.
Neural networks are massively successful in the domain of computer vision. Specifically, convolutional neural networks(CNNs) take images and extract relevant features from them by using small windows that travel over the image. This understanding can be leveraged to identify objects from your camera (Google Lens) and, in the future, even drive your car (NVIDIA).

原文链接:https://medium.com/datalogue/attention-in-keras-1892773a4f22


本文转载自:http://www.jianshu.com/p/91a72437a1bf

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
JavaAutoDeploy工具使用及BUG

JavaAutoDeploy工具使用及BUG 管理原理流程模型: 管理机安装好jdk环境 被管理机开启ssh及相应的端口 管理机新建代码存放目录 mkdir /data/release/20170805/app 把程序需要更新的代码及文件...

香小草
2017/12/29
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
首期腾讯AI加速器毕业 9个月项目总估值翻3倍

  4月11日晚,首期腾讯AI加速器毕业典礼在重庆举行。从上千个国内AI创业项目中精选出25个项目以及从海外AI大赛选拔出的4个项目经过9个月加速,整体估值从70亿增至200多亿,翻了近3倍。其中...

机器之心
04/13
0
0
区块链技术让科学家共享患者健康资讯,同时保障个人资料安全

【Technews科技新报】目前医生在依据乳房摄影判断乳癌发生的情况下,有四分之一的乳癌无法被及时判断发现。为了提升乳癌确诊的效率,科学家计划以数百万包含了健康女性以及患有乳癌的女性乳房...

黄 斯沛
04/16
0
0

没有更多内容

加载失败,请刷新页面

加载更多

活动招募 HUAWEI HiAI公开课·北京站-如何在4小时把你的APP变身AI应用

人工智能和机器学习是全球关注的新趋势,也是当前最火爆、最流行的话题。当你拿手机用语音助手帮你点外卖,智能推荐帮你把周边美食一网打尽;当你拿起P20拍照时,它将自动识别场景进行最美优...

华为终端开放实验室
27分钟前
1
0
匹配两位小数,js正则

var regex = /^\d*(\.[1-9]|\.\d[1-9])*$/ console.log(1.2,regex.test(1.2)); console.log(0.3,regex.test(0.3)); console.log(1.03,regex.test(1.03)); ......

微信小程序-暗潮
31分钟前
1
0
905. Sort Array By Parity - LeetCode

Question 905. Sort Array By Parity Solution 题目大意:数组排序,偶数放前,奇数在后,偶数的数之间不用管顺序,奇数的数之间也不用管顺序 思路:建两个list,一个放偶数,一个放奇数,最...

yysue
36分钟前
1
0
h5 禁止手机自带键盘弹出

html: <div style="width: 350px;margin:50px auto;"><input type="text" id="datePicker" class="date_picker form-control" placeholder="点击选择入住日期" /></div> js: $("#date......

Delete90
53分钟前
1
0
color透明度对照表

透明度百分比 数值 100% 不透明 FF 95% F2 90% E6 85% D9 80% CC 75% BF 70% B3 65% A6 60% 99 55% 8C 50% 80 45% 73 40% 66 35% 59 30% 4D 25% 40 20% 33 15% 26 10% 1A 5% 0D 0% 完全透明 ......

_无问西东
54分钟前
1
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