somTian-CSDN博客

原创 keras解决多标签分类问题

multi-class classification problem：多分类问题是相对于二分类问题（典型的0-1分类）来说的，意思是类别总数超过两个的分类问题，比如手写数字识别mnist的label总数有10个，每一个样本的标签在这10个中取一个。multi-label classification problem：多标签分类（或者叫多标记分类），是指一个样本的标签数量不止一个，即一个样本对...

2018-03-19 17:18:47 22120 12

翻译机器学习项目流程清单

机器学习流程

2018-03-16 21:35:30 1446

原创 keras中的损失函数

mean_squared_errormean_absolute_errormean_absolute_percentage_errormean_squared_logarithmic_errorsquared_hingehingecategorical_hingelogcoshcategorical_crossentropysparse_categorical_crosse...

2018-03-16 17:07:20 10972

原创 Mysql 中的group_concat函数的使用及陷阱

group_concat函数长度限制

2017-12-04 10:19:54 1097

原创科学研究设计七：单案例设计

在应用行为分析领域单案例实验设计

2017-11-18 09:06:50 6961

原创科学研究设计六：有效性威胁

内部有效性和外部有效性

2017-11-18 08:46:51 17853

原创科学研究设计五：实验设计

如何做科学研究的实验设计

2017-11-18 08:41:43 12663

原创科学研究设计四：测量

变量测量

2017-11-17 22:25:28 3124

原创科学研究设计三：抽样

抽样

2017-11-17 22:18:07 3142

原创科学研究设计二：定量分析和定性分析

定量分析和定性分析

2017-11-17 22:13:55 21349

原创科学研究设计一：什么是科学

什么是科学？理论和假设

2017-11-17 22:09:20 3102

原创机器学习常用数学公式

常用的数学公式、指标的latax格式，不断更新中

2017-10-28 10:31:22 1138

翻译推荐系统研究中的九大数据集

一直想做一个工程，整理下推荐系统的相关数据集，现在看到一片英文博客，介绍了九个数据集，就翻译过来了，后续会把自己的整理的数据都整理下发上来

2017-09-17 19:52:18 9742

原创 Ubuntu 下mysql数据库存放位置迁移

Ubuntu 环境下mysql数据库的存放位置迁移。

2017-07-18 20:25:58 3479 2

翻译 [论文学习]Private traits and attributes are predictable from digital records of human behavior

从用户的网络行为记录中预测用户的偏好和属性信息，通过facebook likes可以推断用户的性别、爱好、年龄、宗教等等信息。

2017-07-10 11:40:10 1870

翻译 Recommendation System Algorithms

翻译自国外一篇博客，这篇博客对于当下推荐系统中使用到的协同过滤、矩阵分解、聚类和深度学习的方法进行了一个简单的介绍，方便大家入门推荐系统和了解主流方法

2017-07-09 21:11:03 1178

原创 [论文学习]An Effective Approach for Mining Mobile User Habits：一种高效挖掘移动用户习惯的方法

最后收到一份移动用户行为的大数据，初步进行一下用户行为建模。如何针对用户在设备上的行为记录进行建模分析，是进行用户画像、个性化推荐和精准营销的基础，因此最近看了几篇用户行为建模的文章。

2017-07-08 18:28:29 923

原创英文文献及论文写作中的一些技巧

英文文献写作助手

2017-07-07 21:49:05 1055

原创 hive使用中踩的一些坑

hive使用过程中遇到的一些问题和解决方法

2017-06-30 16:51:54 2034

翻译 [论文学习]Deep Learning Based Recommendation: A Survey

这篇文章总结了近年来深度学习在推荐系统上的应用，并按照输入输出进行了分类，可以对深度学习如何运用到推荐系统上有一个大概的认识

2017-06-22 18:17:05 1080

原创深度学习理论与技术的重点研究方向

下一代深度学习的重点研究方向，出自科技部变革性技术关键科学问题重点专项2017年度项目申报指南建议

2017-06-21 16:40:25 4248

翻译 RecSys’16 Workshop on Deep Learning for Recommender Systems (DLRS)

RecSys’16 Workshop on Deep Learning for Recommender Systems 翻译

2017-06-19 21:05:47 949

原创 centos7 同时安装python2、python3和pip3以及各种包遇到的坑

centos7自带python2.7.5，这基本上够用了，但是python2在处理中文数据时很容易遇到编码问题，编码问题是在让人头疼，所以果断安装python3，python3对于utf-8的支持还是很强的，起码在使用gensim包处理中文时没有遇到编码的问题。因此，在我们的服务器上加装了python3.4，但是由此引发了一系列的坑

2017-06-09 10:54:28 5553

翻译应用到文本领域的卷积方法

本文介绍了文本领域的相关任务和技术，探讨了循环神经网络在文本领域的优势，并进一步研究了应用在文本领域的卷积网络方法，原文地址：https://medium.com/@TalPerry/convolutional-methods-for-text-d5260fd5675f

2017-05-27 15:49:52 4461

翻译 [论文学习]Convolutional matrix factorization for document context-aware recommendation

翻译论文Convolutional matrix factorization for document context-aware recommendation

2017-05-23 20:57:24 7235 1

原创 hive mysql 数据传输

sqoop 将hive中的数据表导出到mysql中：

2017-05-22 19:03:53 578

翻译生成对抗网络的简单介绍（TensorFlow 代码）

原文地址：An introduction to Generative Adversarial Networks (with code in TensorFlow) 最近，研究者们对生成模型的兴趣一直很大。这些生成模型是可以学习创建类似于我们给它们的数据。

2017-05-15 12:15:11 12909 1

原创 Generative Adversarial Networks 生成对抗网络的简单理解

这几年在机器学习领域最亮最火最耀眼的新思想就是生成对抗网络了。这一思想不光催生了很多篇理论论文，也带来了层出不穷的实际应用。Yann LeCun 本人也曾毫不吝啬地称赞过：这是这几年最棒的想法！

2017-05-13 10:01:14 1633

翻译当推荐系统遇上深度学习

Deep Learning Meets Recommendation Systems 深度学习推荐系统电影海报

2017-05-10 11:57:10 16455 6

翻译 Tensorflow实现的CNN文本分类

翻译自博客：IMPLEMENTING A CNN FOR TEXT CLASSIFICATION IN TENSORFLOW 使用Tensorflow实现一个类似于Kim Yoon的卷积神经网络语句分类的模型。

2017-04-05 21:39:13 18143 6

原创深度学习：几个重要的数学概念

机器学习的几个概念

2017-03-10 10:03:35 5210

原创 Tensorflow学习：使用Tensorflow搭建深层网络分类器

使用Tensorflow的高级API - tf.contrib.learn 搭建一个DNN分类器

2017-03-08 09:53:02 1069

原创 Udacity DEEPLEARNING 学习笔记 L4 TEXT AND SEQUENCE MODEL

L4 TEXT AND SEQUENCE MODEL

2016-11-13 21:29:52 1099

原创 Udacity DEEPLEARNING 学习笔记 L3 CONVOLUTIONAL NEURAL NETWORKS

L3 CONVOLUTIONAL NEURAL NETWORKS

2016-11-13 21:20:38 1081

原创 Udacity DEEPLEARNING 学习笔记 L2 DEEP NEURAL NETWORK

L2 DEEP NEURAL NETWORK

2016-11-13 21:08:17 1325

原创 Udacity DEEPLEARNING 学习笔记 L1 Mechine Learning to DeepLearning

L1 Mechine Learning to DeepLearning

2016-11-13 21:00:50 2300

原创 deeplearning论文学习笔记（2）A critical review of recurrent neural networks for sequence learning

RNN的综述

2016-10-26 10:25:04 1075

原创公开课资源

1.在B站好好学习

2016-10-22 20:42:23 772

原创 word2vec的使用参数解释和应用场景

word2vec + Cywin + windows sever，

2016-08-12 17:56:32 3319

原创 deeplearning论文学习笔记（1）Convolutional Neural Networks for Sentence Classification

论文笔记

2016-08-08 16:05:52 1278

Learning Representation for Multi-View Data Analysis

This book equips readers to handle complex multi-view data representation, centered around several major visual applications, sharing many tips and insights through a unified learning framework. This framework is able to model most existing multi-view learning and domain adaptation, enriching readers’ understanding from their similarity, and differences based on data organization and problem settings, as well as the research goal. A comprehensive review exhaustively provides the key recent research on multi-view data analysis, i.e., multi-view clustering, multi-view classification, zero-shot learning, and domain adaption. More practical challenges in multi-view data analysis are discussed including incomplete, unbalanced and large-scale multi-view learning. Learning Representation for Multi-View Data Analysis covers a wide range of applications in the research fields of big data, human-centered computing, pattern recognition, digital marketing, web mining, and computer vision.

2018-12-23

Practical Machine Learning with Python

Practical Machine Learning with Python is a problem solver’s guide to building real-world intelligent systems. It follows a comprehensive three-tiered approach packed with concepts, methodologies, hands-on examples, and code. This book helps its readers master the essential skills needed to recognize and solve complex problems with Machine Learning and Deep Learning by following a data-driven mindset. Using real-world case studies that leverage the popular Python Machine Learning ecosystem, this book is your perfect companion for learning the art and science of Machine Learning to become a successful practitioner. The concepts, techniques, tools, frameworks, and methodologies used in this book will teach you how to think, design, build, and execute Machine Learning systems and projects successfully.

2018-03-28

Data Analysis, Machine Learning and Applications

作者: Preisach, Christine (EDT)/ Burkhardt, Hans (EDT)/ Schmidt-thieme, Lars (EDT) 出版社: Springer Berlin Heidelberg 副标题: Proceedings of the 31st Annual Conference of the Gesellschaft für Klassifikation e.V., ... Data Analysis, and Knowledge Organization) 出版年: 2008-10-10 页数: 736 ISBN: 9783540782391

2018-03-19

Artificial Intelligence for Marketing

A straightforward, non-technical guide to the next major marketing tool Artificial Intelligence for Marketing presents a tightly-focused introduction to machine learning, written specifically for marketing professionals. This book will not teach you to be a data scientist—but it does explain how Artificial Intelligence and Machine Learning will revolutionize your company's marketing strategy, and teach you how to use it most effectively. Data and analytics have become table stakes in modern marketing, but the field is ever-evolving with data scientists continually developing new algorithms—where does that leave you? How can marketers use the latest data science developments to their advantage? This book walks you through the "need-to-know" aspects of Artificial Intelligence, including natural language processing, speech recognition, and the power of Machine Learning to show you how to make the most of this technology in a practical, tactical way.

2018-03-17

Bayesian Computation with R

There has been a dramatic growth in the development and application of Bayesian inferential methods. Some of this growth is due to the availability of powerful simulation-based algorithms to summarize posterior distributions. There has been also a growing interest in the use of the system R for statistical analyses. R's open source nature, free availability, and large number of contributor packages have made R the software of choice for many statisticians in education and industry.

2018-03-16

A Statistical View of deep learning

Deep learning and the use of deep neural networks are now established as a key tool for practical machine learning. Neural networks have an equivalence with many existing statistical and machine learning approaches and I would like to explore one of these views in this post. In particular, I'll look at the view of deep neural networks as recursive generalised linear models (RGLMs). Generalised linear models form one of the cornerstones of probabilistic modelling and are used in almost every field of experimental science, so this connection is an extremely useful one to have in mind. I'll focus here on what are called feedforward neural networks and leave a discussion of the statistical connections to recurrent networks to another post.

2018-03-16

空空如也

TA创建的收藏夹 TA关注的收藏夹

TA关注的人