2019年12月_xiewenbo

12月 11月 07月 06月 05月 04月 03月 02月 01月

转载 Dilated/Atrous Convolution

Dilated Convolution(或者叫做 Atrous Convolution), 中文称作空洞卷积/带孔卷积/扩张卷积/膨胀卷积/多孔卷积.这些名称指的都是同一个意思,都是同一种操作.出处Multi-Scale Context Aggregation by Dilated Convolutions为什么需要空洞卷积在出现空洞卷积之前的CNN分割网络中,习惯于使用Pooling...

2019-12-27 22:31:04 196

原创《变分自动编码器在协同过滤中的使用》做推荐召回《Variational Autoencoders for Collaborative Filtering 》

文章主要讲VAE中的隐式反馈在CF中的使用，取top K做为召回。非线性的概率模型可以大大提升模型的表征能力。传统encode-decode框架把Input encode到一个“固定”的编码，然后再利用decode将编码复原到目标，对于未知的输入可能无法decode到有意义的输出，而VAE在encode过程得到一个隐式的分布得到均值和方差两个参数，通过两个参数确定的分布进行采样得到隐变量z，然...

2019-12-26 23:50:41 1193

原创 [PGN]coverageLosss note

2019-12-26 23:45:42 205

原创《Neural Input Search for Large Scale Recommendation Models》笔记

一、综述：起因：推荐场景下，embedding维度太大，参数太多，导致高存储占用，feature embedding的每一维不能有效的训练。本文内容：NIS主要应用推荐场景下（Recall/Rank），输入特征的embedding产生大量的训练参数，而且对于不同的特征以及一个特征的不同值，因为他们的覆盖的样本数据不同，因此这些参数得到train的机会也有不同，对于覆盖高频的特征或特征值用较...

2019-12-26 23:42:58 983

原创因果卷积（causal）与扩展卷积（dilated）

https://www.cnblogs.com/fantastic123/p/9389128.htmlhttps://blog.csdn.net/silence2015/article/details/79748729https://www.jianshu.com/p/f743bd9041b3

2019-12-13 14:21:30 1729

转载 A Painless Q-learning Tutorial (一个 Q-learning 算法的简明教程)

https://blog.csdn.net/itplus/article/details/9361915

2019-12-13 10:53:57 101

转载 FLASK 中如何获取 GET/POST 请求的参数

args 取get参数 account = request.args.get('account')form 取post参数 account = request.form.get('account')一般来说，传递请求参数的方式有两种，一是打包成 JSON 之后再传递，二是直接放进 URL 进行传递。对于第一种方式，一般用 POST 请求来传递参数，然后用 FLASK 中 request ...

2019-12-10 15:33:11 767

转载命名实体识别从数据集到算法实现-标注法记录-技术很旧

命名实体识别（Named Entity Recognition, NER）是 NLP 的基础任务，指从文本中识别出命名性指称项，为关系抽取等任务做铺垫。狭义上，是识别出人名、地名和组织机构名这三类命名实体（时间、货币名称等构成规律明显的实体类型可以用正则等方式识别）。当然，在特定领域中，会相应地定义领域内的各种实体类型。目前的主流工作，是将 NER当做深度学习任务来做，所以，我们需要大量的、高质量...

2019-12-09 19:17:23 1427

原创几种不同的dot/Dot的用法

1.from keras.layers.merge importdotx = tf.constant([[1,2,3]])>>> dot([x,x],axes=1)<tf.Tensor 'dot_8/ExpandDims:0' shape=(1, 1) dtype=int32>2.import tensorflow.keras.ba...

2019-12-04 12:55:27 1993

转载广告点击率的贝叶斯平滑

广告点击率的贝叶斯平滑声明：1）该博文是Yahoo专家所无私奉献的论文资料整理的。具体引用的资料请看参考文献。具体的版本声明也参考原文献2）本文仅供学术交流，非商用。所以每一部分具体的参考资料并没有详细对应，更有些部分本来就是直接从其他博客复制过来的。如果某部分不小心侵犯了大家的利益，还望海涵，并联系老衲删除或修改，直到相关人士满意为止。3）本人才疏学浅，整理总结的时候难免出错，还望...

2019-12-04 10:08:21 309

转载论推荐系统的Exploitation和Exploration

上一篇文章讲到，一个推荐系统，如果片面优化用户的喜好，很可能导致千篇一律的推荐结果。文中曾经用了一节来讨论为什么使用Exploitation & Exploration (E & E)结果可能依然不能“免俗”。其实，E & E是推荐系统里很有意思，但也非常有争议的一个算法。一方面，大家都基本明白这类算法的目的，每年有很多相关论文发表。另一方面，这是工业界对于部署这类算法非常...

2019-12-04 10:06:29 604

转载深入理解AUC

2019-12-03 09:58:43 129

httpclient tutorial httpclient 指南

httpclient 指南包括了详细的调用和常用代码 The Hyper-Text Transfer Protocol (HTTP) is perhaps the most significant protocol used on the Internet today. Web services, network-enabled appliances and the growth of network computing continue to expand the role of the HTTP protocol beyond user-driven web browsers, while increasing the number of applications that require HTTP support. Although the java.net package provides basic functionality for accessing resources via HTTP, it doesn't provide the full flexibility or functionality needed by many applications. HttpClient seeks to fill this void by providing an efficient, up-to-date, and feature-rich package implementing the client side of the most recent HTTP standards and recommendations. Designed for extension while providing robust support for the base HTTP protocol, HttpClient may be of interest to anyone building HTTP-aware client applications such as web browsers, web service clients, or systems that leverage or extend the HTTP protocol for distributed communication.

2018-03-08

mask rcnn paper

We present a conceptually simple, flexible, and general framework for object instance segmentation. Our approach efficiently detects objects in an image while simultaneously generating a high-quality segmentation mask for each instance. The method, called Mask R-CNN, extends Faster R-CNN by adding a branch for predicting an object mask in parallel with the existing branch for bounding box recognition. Mask R-CNN is simple to train and adds only a small overhead to Faster R-CNN, running at 5 fps. Moreover, Mask R-CNN is easy to generalize to other tasks, e.g., allowing us to estimate human poses in the same framework. We show top results in all three tracks of the COCO suite of challenges, including instance segmentation, bounding-box object detection, and person keypoint detection. Without tricks, Mask R-CNN outperforms all existing, single-model entries on every task, including the COCO 2016 challenge winners. We hope our simple and effective approach will serve as a solid baseline and help ease future research in instance-level recognition. Code will be made available.

2018-03-07

Applying Deep Learning To Answer Selection

Applying Deep Learning To Answer Selection- A Study And An Open Task

2018-03-07

Learning Phrase Representations using RNN Encoder–Decoder

Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation

2018-03-07

BPTT BackPropagation Through Time.pdf

BPTT paper This report provides detailed description and necessary derivations for the BackPropagation Through Time (BPTT) algorithm. BPTT is often used to learn recurrent neural networks (RNN). Contrary to feed-forward neural networks, the RNN is characterized by the ability of encoding longer past information, thus very suitable for sequential models. The BPTT extends the ordinary BP algorithm to suit the recurrent neural architecture.

2018-03-07

空空如也

TA创建的收藏夹 TA关注的收藏夹

TA关注的人