文档章节

人工智能资料库:第61辑(20170616)

AllenOR灵感
 AllenOR灵感
发布于 2017/09/10 01:25
字数 607
阅读 2
收藏 0

1.【代码】Visual Question Answering in Pytorch

简介:


This repo was made by Remi Cadene (LIP6) and Hedi Ben-Younes (LIP6-Heuritech), two PhD Students working on VQA at UPMC-LIP6 and their professors Matthieu Cord (LIP6) and Nicolas Thome (LIP6-CNAM). We developped this code in the frame of a research paper called MUTAN: Multimodal Tucker Fusion for VQA which is (as far as we know) the current state-of-the-art on the VQA-1 dataset.
The goal of this repo is two folds:

  • to make it easier to reproduce our results,
  • to provide an efficient and modular code base to the community for further research on other VQA datasets.

If you have any questions about our code or model, don't hesitate to contact us or to submit any issues. Pull request are welcome!

原文链接:https://github.com/Cadene/vqa.pytorch


2.【博客】Why Does Deep Learning Not Have a Local Minimum?

简介:


Yes, there is a ‘theoretical justification’, and has taken a couple decades to flush it out.

I will first point out, however, it has been observed in practice. This was pointed out by LeCun in his early work on LeNet, and is actually discussed in the ‘orange book’, “Pattern Classification” by David G. Stork, Peter E. Hart, and Richard O. Duda.

原文链接:http://www.kdnuggets.com/2017/06/deep-learning-local-minimum.html


3.【博客】Graph-based machine learning: Part I

简介:

During the seven-week Insight Data Engineering Fellows Program recent grads and experienced software engineers learn the latest open source technologies by building a data platform to handle large, real-time datasets.

Sebastien Dery (now a Data Science Engineer at Yewno) discusses his project on community detection on large datasets.

原文链接:https://blog.insightdatascience.com/graph-based-machine-learning-6e2bd8926a0


4.【博客】Deep Learning the Stock Market

简介:


In the past few months I’ve been fascinated with “Deep Learning”, especially its applications to language and text. I’ve spent the bulk of my career in financial technologies, mostly in algorithmic trading and alternative data services. You can see where this is going.

I wrote this to get my ideas straight in my head. While I’ve become a “Deep Learning” enthusiast, I don’t have too many opportunities to brain dump an idea in most of its messy glory. I think that a decent indication of a clear thought is the ability to articulate it to people not from the field. I hope that I’ve succeeded in doing that and that my articulation is also a pleasurable read.

原文链接:https://medium.com/@TalPerry/deep-learning-the-stock-market-df853d139e02


5.【论文】Deep Learning in Trading

简介:

Current state of the art

  1. LSTM is theholygrail of sequencepredictions.
    A major part of thefinancial modellingis sequenceprediction- whether that?s volatility modelsor volume modelsor thetoughest oneof all - returnprediction models. This is theunderlyingtask insuchproblems - Givenasequenceof values, can wepredict thenext number inthe sequence?
    LSTM modelsnaturally fit this criteria,becauseof its recursivenature.Additionally,thehiddenstateandthe memory cell tremendouslyhelpretaintheuseful featuresof thesequence.

  2. Featureengineeringis thethingof thepast intheeraof neural networks.
    Neural networksarereallygoodat comingup withfeaturesontheir own.A number of peopleinfinance work
    day-in-day-out incomingup withfeatures.Neural netsarepoisedtotakeover this segment of the market.

  3. Neural networksprovideaneasy way tocombine market dataandother datasources.
    Sinceneural netswork inthelatent space,it?s super easy tocombinedyour market datainput withother datasources
    you might have.That canbeanythingfrom sentiment analysis, summaryof SEC filings tovisual or audioinputs.

  4. Additionally,neural networksmakeit easy todo multivariate modelling wheretherearealot of relationships
    betweeninputs,andthereisatime-varyingnaturetoit.

  5. It?s important tounderstand when neural networksdonot work - theydon?t work if youdon?t haveenoughdata.
    Small datasetsarebottleneckswhenit comes toconvergence.Largedatasets come withcomputationproblems.

原文链接:https://qplumproduction.s3.amazonaws.com/uploads/file_download/pdf_file/17/deep-learning-in-trading.pdf


本文转载自:http://www.jianshu.com/p/c97a945124ab

共有 人打赏支持
AllenOR灵感
粉丝 11
博文 2635
码字总数 83001
作品 0
程序员
私信 提问
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
国行版HomePod售价2799元,本周五发售

(图片源自苹果中国官网截图) 整理 | 一一 出品 | AI科技大本营 去年 12 月,苹果表示将于今年年初在中国销售其 HomePod 智能音箱。1 月 14 日,苹果公司正式宣布,HomePod 将于 1 月 18 日...

AI科技大本营
前天
0
0
BAT机器学习面试题及解析(281-285题)

本系列作为国内首个AI题库,囊括绝大部分机器学习和深度学习的笔试面试题、知识点,可以作为机器学习自测题,也可以当做查漏补缺的资料库。七月在线AI题库(网页版及APP版)见“阅读原文” ...

t7sfokzord1jaymsfk4
2017/12/20
0
0
BAT机器学习面试题及解析(271-275题)

本系列作为国内首个AI题库,囊括绝大部分机器学习和深度学习的笔试面试题、知识点,可以作为机器学习自测题,也可以当做查漏补缺的资料库。 271.SVM、LR、决策树的对比。 模型复杂度:SVM支持...

t7sfokzord1jaymsfk4
2017/12/14
0
0

没有更多内容

加载失败,请刷新页面

加载更多

redis高级进阶(2)

本篇主要介绍如下内容 1.redis服务器数据库 2.redis对过期键的处理 3.redis持久化策略 1.redis服务器数据库 redis服务器如果不指定数据库的具体数据,默认是16个数据库。 客户端连接到redis...

求是科技
1分钟前
0
0
js时间Date对象介绍及解决getTime转换为8点的问题

前言   在做时间转换的时候,发现用“2016-04-12”转出来的时间戳是 2016-04-12 08:00的时间点,而不是0点。 new Date('2016-04-12').getTime();// 1460419200000 new Date(1460419...

Jack088
10分钟前
1
0
Dubbo 实践,演进及未来规划

Dubbo 整体介绍 Dubbo 是一款高性能,轻量级的 Java RPC 框架。虽然它是以 Java 语言来出名的,但是现在我们生态里面已经有 Go、Python、PHP、Node.JS 等等语言。 Dubbo 是一个 RPC 框架,它...

微笑向暖wx
10分钟前
0
0
用Python建立最简单的web服务器

前提:已装好python,mac默认已有 参考:https://www.cnblogs.com/xuxn/archive/2011/02/14/build-simple-web-server-with-python.html 利用Python自带的包可以建立简单的web服务器。在DOS里...

Liens
12分钟前
0
0
MaxCompute安全管理指南-基础篇

背景及目的 方便和辅助MaxCompute的project owner或安全管理员进行project的日常安全运维,保障数据安全。 MaxCompute有安全模型,DataWorks也有安全模型,当通过DataWorks使用MaxCompute,而...

阿里云官方博客
21分钟前
2
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