文档章节

人工智能资料库:第59辑(20170607)

AllenOR灵感
 AllenOR灵感
发布于 2017/09/10 01:26
字数 747
阅读 3
收藏 0

1.【博客】Transfer learning & The art of using Pre-trained Models in Deep Learning

简介:

Neural networks are a different breed of models compared to the supervised machine learning algorithms. Why do I say so? There are multiple reasons for that, but the most prominent is the cost of running algorithms on the hardware.

In today’s world, RAM on a machine is cheap and is available in plenty. You need hundreds of GBs of RAM to run a super complex supervised machine learning problem – it can be yours for a little investment / rent. On the other hand, access to GPUs is not that cheap. You need access to hundred GB VRAM on GPUs – it won’t be straight forward and would involve significant costs.

Now, that may change in future. But for now, it means that we have to be smarter about the way we use our resources in solving Deep Learning problems. Especially so, when we try to solve complex real life problems on areas like image and voice recognition. Once you have a few hidden layers in your model, adding another layer of hidden layer would need immense resources.

Thankfully, there is something called “Transfer Learning” which enables us to use pre-trained models from other people by making small changes. In this article, I am going to tell how we can use pre-trained models to accelerate our solutions.

原文链接:https://www.analyticsvidhya.com/blog/2017/06/transfer-learning-the-art-of-fine-tuning-a-pre-trained-model/


2.【代码】Thinc: Practical Machine Learning for NLP in Python

简介:

Thinc is the machine learning library powering spaCy. It features a battle-tested linear model designed for large sparse learning problems, and a flexible neural network model under development for spaCy v2.0.
Thinc is a practical toolkit for implementing models that follow the "Embed, encode, attend, predict" architecture. It's designed to be easy to install, efficient for CPU usage and optimised for NLP and deep learning with text – in particular, hierarchically structured input and variable-length sequences.

原文链接:https://github.com/explosion/thinc


3.【博客】
Neural networks for algorithmic trading. Multivariate time series

简介:


In previous post we discussed several ways to forecast financial time series: how to normalize data, make prediction in the form of real value or binary variable and how to deal with overfitting on highly noisy data. But what we skipped (on purpose) — is that our .csv file with prices basically has much more data that we may use. In last post only close prices with some transformation were used, but what can happen if we will consider also high, low, open prices and volume of every historical day? This leads us to working with multidimensional, e.g. multivariate time series, where on every time stamp we have more than just one variable — in our case we will work with whole OHLCV tuple.

原文链接:https://medium.com/@alexrachnog/neural-networks-for-algorithmic-trading-2-1-multivariate-time-series-ab016ce70f57


4.【博客】How Zendesk Serves TensorFlow Models in Production

简介:

At Zendesk we are developing a series of machine learning products, the most recent of which is Automatic Answers. It uses machine learning to interpret user questions and responds with relevant knowledge base articles. When a customer has a question, complaint or enquiry, they may submit their request online. Once their request is received, Automatic Answers will analyse the request and suggest relevant articles which may best assist with the customer’s request via email.

原文链接:https://medium.com/zendesk-engineering/how-zendesk-serves-tensorflow-models-in-production-751ee22f0f4b


5.【博客】Image Segmentation using deconvolution layer in Tensorflow

简介:

Image segmentation is just one of the many use cases of this layer. In any type of computer vision application where resolution of final output is required to be larger than input, this layer is the de-facto standard. This layer is used in very popular applications like Generative Adversarial Networks(GAN), image super-resolution, surface depth estimation from image, optical flow estimation etc. These are some direct applications of deconvolution layer. It has now also been deployed in other applications like fine-grained recogntion, object detection. In these use cases, the existing systems can use deconvolution layer to merge responses from different convolutional layers and can significantly boosts up their accuracy.

There are 4 main parts of this post:

  1. What is image segmentation?
  2. What is deconvolutional layer?
  3. Initialization strategy for deconvolutional layer.
  4. Writing a deconvolutional layer for Tensorflow.

原文链接:http://cv-tricks.com/image-segmentation/transpose-convolution-in-tensorflow/


本文转载自:http://www.jianshu.com/p/cc939baf298d

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
百度市值暴涨70多亿,看来京东梦碎了!

  【IT168 评论】10天前,京东市值与百度仅差一个涨停板。10天之内,百度市值大涨70多亿美金。截至美东时间7月3日13:00:00,百度总市值为624.98亿,京东总市值为551.59亿。截至发稿前,双...

it168网站
2017/07/06
0
0
央行加强互联网金融风险防范化解 腾讯为金融云入股长亮科技 | AI金融评论晚报

央行:继续做好互联网金融风险防范化解 雷锋网(公众号:雷锋网)AI金融评论消息,人民银行相关负责人23日在防范和处置非法集资法律政策宣传座谈会上介绍,当前互联网金融领域非法集资形势呈现...

AI金融评论
04/23
0
0
AI入侵服装业后一大批“铁饭碗”面临下岗!

人工智能(AI)技术在时尚行业的应用正在越来越深入、广泛,凭借这项技术不仅可以设计服装,还可以精确规划库存。现在,甚至有人开始担心,人工智能是否会彻底取代那些精英白领,从事高技术含量...

六库科技
08/16
0
0

没有更多内容

加载失败,请刷新页面

加载更多

day99-20180926-英语流利阅读-待学习

换汤不换药的美容大忽悠:从抗衰老到肌肤焕发新生 Lala 2018-09-26 1.今日导读 说到护肤品,一个个大牌广告就浮现在我们眼前:皮肤吹弹可破的女明星手捧功能各异的瓶瓶罐罐,暗示着消费者买买...

飞鱼说编程
33分钟前
3
0
FFmpeg Maintainer赵军:FFmpeg关键组件与硬件加速

大家好!我是赵军,现就职于英特尔的DCG从事基于FFmpeg的硬件优化工作,两年多前加入FFmpeg社区,2018年4月成为FFmpeg的其中的一个FFmpeg Maintainer,主要负责FFmpeg的硬件优化工作。 概览:...

yizhichao
今天
1
0
ehlib 修改 使行号字体颜色 与标题字体颜色 一致

对ehlib 显示效果不够满意,而做的调整 修改这个过程:procedure TCustomDBGridEh.DrawIndicatorCell(ACol, ARow: Longint; AreaCol, AreaRow: Longint; ARect: TRect; AState: TGri......

vga
今天
1
0
Bash重定向详解

Bash重定向详解 Bash的重定向指的是将命令的输入和输出导向不同地方,而不是默认的标准输入、标准输出和标准错误。Bash的重定向实际上是对标准输入、标准输出和标准错误的重置,进而将所需输...

小陶小陶
今天
3
0
EventBus原理深度解析

一、问题描述 在工作中,经常会遇见使用异步的方式来发送事件,或者触发另外一个动作:经常用到的框架是MQ(分布式方式通知)。如果是同一个jvm里面通知的话,就可以使用EventBus。由于Event...

yangjianzhou
今天
54
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