文档章节

人工智能资料库:第12辑(20170120)

AllenOR灵感
 AllenOR灵感
发布于 2017/09/10 01:27
字数 1029
阅读 2
收藏 0

  1. 【博客】Understanding the new Google Translate

简介:


Google launched a new version of the Translate in September 2016. Since then, there have been a few interesting developments in the project, and this post attempts to explain it all in as simple terms as possible.

The earlier version of the Translate used Phrase-based Machine Translation, or PBMT. What PBMT does is break up an input sentence into a set of words/phrases and translate each one individually. This is obviously not an optimal strategy, since it completely misses out on the context of the overall sentence. The new Translate uses what Google calls *Google Neural Machine Translation (*GNMT**), an improvement over a traditional version of NMT. Lets see how GNMT works on a high-level:

原文链接:https://codesachin.wordpress.com/2017/01/18/understanding-the-new-google-translate/


2.【博客 & 代码】Self-Organizing Maps with Google’s TensorFlow

简介:

A Self-Organizing Map, or SOM, falls under the rare domain of unsupervised learning in Neural Networks. Its essentially a grid of neurons, each denoting one cluster learned during training. Traditionally speaking, there is no concept of neuron ‘locations’ in ANNs. However, in an SOM, each neuron has a location, and neurons that lie close to each other represent clusters with similar properties. Each neuron has a weightage vector, which is equal to the centroid of its particular cluster.

原文链接:https://codesachin.wordpress.com/2015/11/28/self-organizing-maps-with-googles-tensorflow/

原理链接:http://www.ai-junkie.com/ann/som/som1.html


3.【博客】Simple Beginner’s guide to Reinforcement Learning & its implementation

简介:

这篇博客,我近期会把它翻译成中文,并且做一个学习笔记。

One of the most fundamental question for scientists across the globe has been – “How to learn a new skill?”. The desire to understand the answer is obvious – if we can understand this, we can enable human species to do things we might not have thought before. Alternately, we can train machines to do more “human” tasks and create true artificial intelligence.

While we don’t have a complete answer to the above question yet, there are a few things which are clear. Irrespective of the skill, we first learn by interacting with the environment. Whether we are learning to drive a car or whether it an infant learning to walk, the learning is based on the interaction with the environment. Learning from interaction is the foundational underlying concept for all theories of learning and intelligence.

原文链接:https://www.analyticsvidhya.com/blog/2017/01/introduction-to-reinforcement-learning-implementation/


4.【论文】Revisiting Visual Question Answering Baselines

简介:

Visual question answering (VQA) is an interesting learning setting for evaluating the abilities and shortcomings of current systems for image understanding. Many of the recently proposed VQA systems include attention or memory mechanisms designed to support “reasoning”. For multiple-choice VQA, nearly all of these systems train a multi-class classifier on image and question features to predict an answer. This paper questions the value of these common practices and develops a simple alternative model based on binary classification. Instead of treating answers as competing choices, our model receives the answer as input and predicts whether or not an image-question-answer triplet is correct. We evaluate our model on the Visual7W Telling and the VQA Real Multiple Choice tasks, and find that even simple versions of our model perform competitively. Our best model achieves state-of-the-art performance on the Visual7W Telling task and compares surprisingly well with the most complex systems proposed for the VQA Real Multiple Choice task. We explore variants of the model and study its transferability between both datasets. We also present an error analysis of our model that suggests a key problem of current VQA systems lies in the lack of visual grounding of concepts that occur in the questions and answers. Overall, our results suggest that the performance of current VQA systems is not significantly better than that of systems designed to exploit dataset biases.

原文链接:https://arxiv.org/pdf/1606.08390v2.pdf


5.【Tutorial & 代码】Introduction to Natural Language Processing with fastText

简介:

这篇博客,我近期会把它翻译成中文,并且做一个学习笔记。

Natural Language Processing (NLP) is one of the hottest areas in machine learning. Its global purpose is to understand language the way humans do. NLP subareas include machine translation, text classification, speech recognition, sentiment analysis, question answering, text-to-speech, etc.

As in most areas of Machine Learning, NLP accuracy has improved considerably thanks to deep learning. Just to highlight the most recent and impressive achievement, in October 2016 Microsoft Research reached human parity in speech recognition. For that milestone, they used a combination of Convolutional Neural Networks and LSTM networks.

However, not all machine learning is deep learning, and in this notebook I would like to highlight a great example. In the summer of 2016, two interesting NLP papers were published by Facebook Research, Bojanowski et al., 2016 and Joulin et al., 2016. The first one proposed a new method for word embedding and the second one a method for text classification. The authors also opensourced a C++ library with the implementation of these methods, fastText, that rapidly attracted a lot of interest.

The reason for this interest is that fastText obtains an accuracy in text classification almost as good as the state of the art in deep learning, but it is several orders of magnitude faster. In their paper, the authors compare the accuracy and computation time of several datasets with deep nets. As an example, in the Amazon Polarity dataset, fastText achieves an accuracy of 94.6% in 10s. In the same dataset, the crepe CNN model of Zhang and LeCun, 2016 achieves 94.5% in 5 days, while the Very Deep CNN model of Conneau et al., 2016 achieves 95.7% in 7h. The comparison is not even fair, because while fastText's time is computed with CPUs, the CNN models are computed using Tesla K40 GPUs.

原文链接:https://github.com/miguelgfierro/sciblog_support/blob/master/Intro_to_NLP_with_fastText/Intro_to_NLP.ipynb


本文转载自:http://www.jianshu.com/p/ec20a33aa2f2

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
资源 | 剑桥大学:156页PPT全景展示AI过去的12个月(附下载)

  转载自专知   作者:Nathan Benaich、Ian Hogarth      剑桥大学 Nathan Benaich 与 Ian Hogarth 博士共同发布关于人工智能最近 12 个月进展的报告,其中包含对新技术,人才流动,...

机器之心
07/03
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
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
Jetty 9.4.1, Jetty 9.3.16 和 Jetty 9.2.21 发布

Jetty 9.4.1, Jetty 9.3.16 和 Jetty 9.2.21 发布了。 Jetty 是一个开源的 servlet 容器,它为基于 Java 的 web 内容,例如 JSP 和 servlet 提供运行环境。Jetty 是使用 Java 语言编写的,它...

达尔文
2017/01/24
1K
1

没有更多内容

加载失败,请刷新页面

加载更多

Shell编程(expect同步文件、指定host和同步文件、构建文件分发系统、批量执行命令)

expect脚本同步文件 需求:自动同步文件 实验准备: A机器:192.168.248.130 B机器:192.168.248.129 实现: 1.A机器编写4.expect脚本文件,内容如下所示: #!/usr/bin/expectset passwd "...

蛋黄_Yolks
17分钟前
1
0
ppwjs之bootstrap颜色:背景颜色

<!DOCTYPT html><html><head><meta http-equiv="content-type" content="text/html; charset=utf-8" /><title>ppwjs欢迎您</title><link rel="icon" href="/favicon.ico" ......

ppwjs
18分钟前
0
0
Ubuntu与 Fedora之对比

大家好。今天我将重点介绍两个流行的Linux发行版之间的一些特性和差异; Ubuntu 18.04和Fedora 28。它们都有自己的包管理; Ubuntu使用DEB,而Fedora使用RPM,但它们都具有相同的桌面环境(GNO...

linuxprobe16
22分钟前
1
0
线性代数入门

线性代数的概念对于理解机器学习背后的原理非常重要,尤其是在深度学习领域中。它可以帮助我们更好地理解算法内部到底是怎么运行的,借此,我们就能够更好的做出决策。所以,如果你真的希望了...

牛奋Debug
昨天
3
0
开发5分钟,调试2小时 - 该如何debug?

几年来我在答疑群、论坛、公众号、知乎回答的各种问题,没有一万也有八千。其中有三分之二以上都是在帮人看报错,帮人 debug(调试代码)。 可以说,会不会 debug,有没有 debug 的意识,懂不...

crossin
昨天
4
1

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