文档章节

人工智能资料库:第22辑(20170131)

AllenOR灵感
 AllenOR灵感
发布于 2017/09/10 01:20
字数 752
阅读 2
收藏 0

  1. 【视频】Can Cognitive Neuroscience Provide a Theory of Deep Learning

简介:

本视频主要讲解了认知神经科学对深度学习的理论支持。

原文链接:https://www.youtube.com/watch?v=Zh4A4Lb9jk8&feature=youtu.be

PPT链接:http://www.slideshare.net/SessionsEvents/ted-willke-sr-principal-engineer-intel


2.【博客】Preparing a large-scale image dataset with TensorFlow's tfrecord files

简介:

There are several methods of reading image data in TensorFlow as mentioned in its documentation:

From disk: Using the typical feed_dict argument when running a session for the train_op. However, this is not always possible if your dataset is too large to be held in your GPU memory for it to be trained.

From CSV Files: Not as relevant for dealing with images.

From TFRecord files: This is done by first converting images that are already properly arranged in sub-directories according to their classes into a readable format for TensorFlow, so that you don’t have to read in raw images in real-time as you train. This is much faster than reading images from disk.

原文链接:https://kwotsin.github.io/tech/2017/01/29/tfrecords.html


3.【论文】Optimization Methods for Large-Scale Machine Learning

简介:

This paper provides a review and commentary on the past, present, and future of numerical optimization algorithms in the context of machine learning applications. Through case studies on text classification and the training of deep neural networks, we discuss how optimization problems arise in machine learning and what makes them challenging. A major theme of our study is that large-scale machine learning represents a distinctive setting in which the stochastic gradient (SG) method has traditionally played a central role while conventional gradient-based nonlinear optimization techniques typically falter. Based on this viewpoint, we present a comprehensive theory of a straightforward, yet versatile SG algorithm, discuss its practical behavior, and highlight opportunities for designing algorithms with improved performance. This leads to a discussion about the next generation of optimization methods for large-scale machine learning, including an investigation of two main streams of research on techniques that diminish noise in the stochastic directions and methods that make use of second-order derivative approximations.

原文链接:https://arxiv.org/pdf/1606.04838v1.pdf


4.【问答】41 Essential Machine Learning Interview Questions (with answers)

简介:

Machine learning interview questions are an integral part of the data science interview and the path to becoming a data scientist, machine learning engineer or data engineer. Springboardcreated afree guide to data science interviewsso we know exactly how they can trip candidates up! In order to help resolve that, here is a curated and created a list of key questions that you could see in a machine learning interview. There aresome answers to go along with them so you don’t get stumped. You’ll be able to do well in any job interview with machine learning interview questions after reading through this piece.

原文链接:https://www.springboard.com/blog/machine-learning-interview-questions/


5.【代码】Word Prediction using Convolutional Neural Networks

简介:

In this project, we examine how well neural networks can predict the current or next word. Language modeling is one of the most important nlp tasks, and you can easily find deep learning approaches to it. Our contribution is threefold. First, we want to make a model that simulates a mobile environment, rather than having general modeling purposes. Therefore, instead of assessing perplexity, we try to save the keystrokes that the user need to type. To this end, we manually typed 64 English paragraphs with a iPhone 7 for comparison. It was super boring, but hopefully it will be useful for others. Next, we use CNNs instead of RNNs, which are more widely used in language modeling tasks. RNNs—even improved types such as LSTM or GRU—suffer from short term memory. Deep layers of CNNs are expected to overcome the limitation. Finally, we employ a character-to-word model here. Concretely, we predict the current or next word, seeing the preceding 50 characters. Because we need to make a prediction at every time step of typing, the word-to-word model dont't fit well. And the char-to-char model has limitations in that it depends on the autoregressive assumption. Our current belief is the character-to-word model is best for this task. Although our relatively simple model is still behind a few steps iPhone 7 Keyboard, we observed its potential.

原文链接:https://github.com/Kyubyong/word_prediction


本文转载自:http://www.jianshu.com/p/ee80130837f3

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
GIAC 2017全球互联网架构大会

12月22至23日,GIAC全球互联网架构大会将在上海举行。GIAC 全球互联网架构大会是高可用架构技术社区推广的面向架构师、技术负责人及高端技术从业人员的技术架构大会。GIAC于2016年12月成功举...

活动家
2017/11/24
2
0
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
2018第四范式人工智能+新媒体论坛

2018首届人工智能+新媒体峰会将于11月6日在Blue Note Beijing举办。人民日报新媒体中心丁伟、原新华社新媒体中心总经理现中国搜索党委书记李俊、罗辑思维联合创始人李俊、凤凰新媒体客户端总...

第四范式
10/25
0
0

没有更多内容

加载失败,请刷新页面

加载更多

js垃圾回收机制和引起内存泄漏的操作

JS的垃圾回收机制了解吗? Js具有自动垃圾回收机制。垃圾收集器会按照固定的时间间隔周期性的执行。 JS中最常见的垃圾回收方式是标记清除。 工作原理:是当变量进入环境时,将这个变量标记为“...

Jack088
昨天
2
0
大数据教程(10.1)倒排索引建立

前面博主介绍了sql中join功能的大数据实现,本节将继续为小伙伴们分享倒排索引的建立。 一、需求 在很多项目中,我们需要对我们的文档建立索引(如:论坛帖子);我们需要记录某个词在各个文...

em_aaron
昨天
3
0
"errcode": 41001, "errmsg": "access_token missing hint: [w.ILza05728877!]"

Postman获取微信小程序码的时候报错, errcode: 41001, errmsg: access_token missing hint 查看小程序开发api指南,原来access_token是直接当作parameter的(写在url之后),scene参数一定要...

两广总督bogang
昨天
7
0
MYSQL索引

索引的作用 索引类似书籍目录,查找数据,先查找目录,定位页码 性能影响 索引能大大减少查询数据时需要扫描的数据量,提高查询速度, 避免排序和使用临时表 将随机I/O变顺序I/O 降低写速度,占用磁...

关元
昨天
7
0
撬动世界的支点——《引爆点》读书笔记2900字优秀范文

撬动世界的支点——《引爆点》读书笔记2900字优秀范文: 作者:挽弓如月。因为加入火种协会的读书活动,最近我连续阅读了两本论述流行的大作,格拉德威尔的《引爆点》和乔纳伯杰的《疯传》。...

原创小博客
昨天
21
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