- 博客(42)
- 资源 (5)
- 收藏
- 关注
RSS订阅原创 抢茅台脚本已经被迫下架，你还能抢到心仪的茅台吗？
早上一打开jd seckill就发现这个项目已经凉凉，不过没关系，我从fork了源码的同学手里找到了最新的代码，继续能用起来。期待狗东不会那么快修改后台逻辑。想要最新的源码吗？微信搜索【猿起缘落】，回复【京东】或【茅台】获取最近抢maotai脚本...
2021-01-06 17:27:33
867
翻译 智能无线网络的深度学习：一项综合调查
摘要作为一种有前途的机器学习工具，用于处理复杂原始数据的精确模式识别，深度学习（DL）正成为向大规模拓扑和复杂无线电传输的无线网络添加智能的有效方法。DL使用许多神经网络层来实现从高维原始数据中快速提取特征。 它可以用于根据大量网络参数（如延迟，丢失率，链路SNR等）的分析来查找网络动态（如热点，干扰分布，拥塞点，流量瓶颈，频谱可用性等）。 因此，DL可以分析具有多个节点和动态链路质量的极其...
2019-05-24 10:01:12
6142
原创 特征工程-数据处理
特征工程连续型变量连续变量无量纲化连续变量数据变换连续变量离散化类别变量时间型、日期型变量缺失值处理特征组合连续型变量处理什么是连续型变量？在一定区间内可以任意取值的变量叫连续变量,其数值是连续不断的,相邻两个数值可作无限分割,即可取无限个数值.例如,生产零件的规格尺寸,人体测量的身高,体重,胸围等为连续变量,其数值只能用测量或计量的方法取得.连续变量无量纲化统...
2019-03-17 11:35:34
1236
翻译 机器学习和深度学习中如何处理数据不平衡问题
如何处理数据不平衡问题前言在您正在处理数据集时您可以创建分类模型并立即获得90％的准确度。你觉得“非常不错”。但是当你深入一点时，发现90％的数据属于一个类。这是一个不平衡数据集的例子，它可能导致令人沮丧的结果。当你发现你的数据有不平衡的类并且你认为你得到的所有好的结果都变成了错误的时候，你会感到非常沮丧。当你发现大部分书籍，文章和博客文章似乎并没有为您提供有关处理数据不平衡的良好建议时...
2019-01-25 11:39:24
3737
原创 自动获取https签名
说明[domain] 为网站域名，注意对应修改准备工作安装openssl创建存放ssl证书文件夹mkdir ssl创建账号openssl genrsa 4096 > account.key创建CSR文件创建域名私钥openssl genrsa 4096 > [domain].key生成 CSR 文件单域名openssl req -new -sha...
2019-01-25 10:16:21
538
原创 LSTM的神奇之处
前言LSTM神经网络代表长期短期记忆，是一种特殊类型的递归神经网络，最近在机器学习界引起了很多关注。简而言之，LSTM网络内部具有一些上下文状态单元，它们充当长期或短期存储器单元。LSTM网络的输出由这些单元的状态调制而成。当我们的神经网络需要依赖于输入的历史背景而不是仅仅依赖于最后的输入进行预测时，这是一个非常重要的属性。举个简单的例子，设想我们想要预测一个序列的下一个数字：6 ->...
2018-12-27 11:13:00
476
原创 机器学习面试
主题模型词向量何为词向量？即对词典 D 中任意词 w，指定一个固定长度的实值向量 V(w)属于 R^m 。则 V(w) 即称为w的词向量，m是词向量的长度。词向量有两种表现形式：One-hot Representation：用维度为字典长度的向量表示一个词，仅一个分量为1，其余为0。缺点是容易收到维度灾难的困扰，而且不能很好的刻画词与词之间的关系。Distributed Represe...
2018-12-27 09:49:01
447
原创 GBM参数详解
GBM(gradient boosting machine)参数详解:树参数min_samples_split定义了树中一个节点所需要用来分裂的最少样本数。可以避免过度拟合(over-fitting)。如果用于分类的样本数太小，模型可能只适用于用来训练的样本的分类，而用较多的样本数则可以避免这个问题。但是如果设定的值过大，就可能出现欠拟合现象(under-fitting)。因此我...
2018-12-27 09:42:47
3637
转载 人工智能将如何在2019年改变零售业(How AI Will Change Brick-and-Mortar Retail in 2019)
Data science, machine learning, and AI have clear applications for e-commerce, and given their relative ease of implementation, most online retailers are already deeply invested in strategies like rec...
2018-12-27 09:24:08
737
转载 What is a p-value
While I was refreshing my stats knowledge recently, I had some challenges following along with the explanation that was given in class, so I decided to write one out for myself for future reference....
2018-08-24 10:17:56
1453
转载 Call an Amazon SageMaker model endpoint using Amazon API Gateway and AWS Lambda
At AWS Machine Learning workshops, customers often ask, “After I deploy an endpoint, where do I go from there?” You can deploy an Amazon SageMaker trained and validated machine learning model as an en...
2018-08-24 10:17:10
585
转载 2018-08-22 Whats new on arXiv
Use Of Vapnik-Chervonenkis Dimension in Model SelectionIn this dissertation, I derive a new method to estimate the Vapnik-Chervonenkis Dimension (VCD) for the class of linear functions. This method ...
2018-08-24 10:16:11
1099
转载 Distilled News
T2F – Text-to-Face generation using Deep LearningThis project combines two of the recent architectures StackGAN and ProGAN for synthesizing faces from textual descriptions. The project uses Face2Tex...
2018-08-06 17:32:30
259
转载 Scale out your Pandas DataFrame operations using Dask
In Pandas, one can easily apply operations on all the data using the apply method. However, this method is quite slow and is not useful when scaling up your methods. Is there a way to speed up these o...
2018-08-06 17:30:20
218
转载 Essential Tips and Tricks for Starting Machine Learning with Python
“I am a student of computer science/engineering. How do I get into the field of machine learning/deep learning/AI?”It’s never been easier to get started with machine learning. In addition to str...
2018-08-06 17:29:41
309
转载 Scalable multi-node deep learning training using GPUs in the AWS Cloud
A key barrier to the wider adoption of deep neural networks on industrial-size datasets is the time and resources required to train them. AlexNet, which won the 2012 ImageNet Large Scale Visual Recogn...
2018-07-31 10:55:21
330
转载 Visualizing an Assassin Puzzle
Over at Math3ma, Tai-Danae Bradley shared the following puzzle, which she also featured in a fantastic (spoiler-free) YouTube video. If you’re seeing this for the first time, watch the video first....
2018-07-31 10:54:58
222
原创 Spark Transformation和Actions
Transformation和ActionsTransformation具体内容map(func) :返回一个新的分布式数据集，由每个原元素经过func函数转换后组成filter(func) : 返回一个新的数据集，由经过func函数后返回值为true的原元素组成*flatMap(func) : 类似于map，但是每一个输入元素，会被映射为0到多个输出元素（因此，func函数的返回...
2018-07-31 09:21:08
191
转载 Partitioning the Variation in Data
Roger Peng ** 2018/07/23One of the fundamental questions that we can ask in any data analysis is, “Why do things vary?” Although I think this is fundamental, I’ve found that it’s not explicitly as...
2018-07-31 09:19:20
230
转载 Classify your own images using Amazon SageMaker
Image classification and object detection in images are hot topics these days, thanks to a combination of improvements in algorithms, datasets, frameworks, and hardware. These improvements democratize...
2018-07-31 09:18:34
279
转载 The Real Problems with Neural Machine Translation
TLDR: No! Your Machine Translation Model is not “prophesying”, but let’s look at the six major issues with neural machine translation (NMT). So I saw a Twitter thread today with the editor-in-ch...
2018-07-31 09:18:15
199
转载 Basic Statistics in Python： Probability
When studying statistics, you will inevitably have to learn about probability. It is easy lose yourself in the formulas and theory behind probability, but it has essential uses in both working and dai...
2018-07-31 09:17:36
567
转载 Python数据分析之pandas
前面一篇文章我们介绍了numpy，但numpy的特长并不是在于数据处理，而是在它能非常方便地实现科学计算，所以我们日常对数据进行处理时用的numpy情况并不是很多，我们需要处理的数据一般都是带有列标签和index索引的，而numpy并不支持这些，这时我们就需要pandas上场啦！ WHAT?Pandas是基于Numpy构建的库，在数据处理方面可以把它理解为numpy加...
2018-07-30 10:18:54
501
转载 Create a model for predicting orthopedic pathology using Amazon SageMaker
Artificial intelligence (AI) and machine learning (ML) are gaining momentum in the healthcare industry, especially in healthcare imaging. The Amazon SageMaker approach to ML presents promising potenti...
2018-07-30 10:17:16
569
转载 Why AI Isn’t A Black Box (And Its Business Value)
Artificial intelligence (AI) is a powerful and growing field, but some are still hesitant to employ it, seeing it as a black box. However, if you take a second to step outside the box (see what we did...
2018-07-30 10:16:52
180
转载 How To Remotely Send R and Python Execution to SQL Server from Jupyter Notebooks
IntroductionDid you know that you can execute R and Python code remotely in SQL Server from Jupyter Notebooks or any IDE? Machine Learning Services in SQL Server eliminates the need to move data...
2018-07-30 10:16:34
244
转载 Verlet Simulations
  || ||In this article we’re going to look at some simple physics simulations using a technique called Verlet Integration. We’ll start with some basic concepts, build on them, and finish with a...
2018-07-30 10:16:11
484
转载 RAIN Project： evolution of the game development dream
July 12, 2018Four years ago, I started Data School to share my data science knowledge and help aspiring data scientists achieve their dreams. Today, I’m excited to share with you a new opportunity t...
2018-07-30 10:15:48
704
转载 Object Detection algorithm now available in Amazon SageMaker
Amazon SageMaker is a fully-managed and highly scalable machine learning (ML) platform that makes it easy build, train, and deploy machine learning models. This is a giant step towards the democratiza...
2018-07-30 10:15:27
292
转载 Enhanced text classification and word vectors using Amazon SageMaker BlazingText
Today, we are launching several new features for the Amazon SageMaker BlazingText algorithm. Many downstream natural language processing (NLP) tasks like sentiment analysis, named entity recognit...
2018-07-30 10:14:56
346
转载 New Research on Multi-Task Learning
We are excited to share the latest report and prototype from our machine intelligence R team: Multi-Task Learning.Wax on.. face off! When humans learn new tasks, we take advantage of knowledge we’...
2018-07-30 10:14:26
174
转载 Enhanced text classification and word vectors using Amazon SageMaker BlazingText
Today, we are launching several new features for the Amazon SageMaker BlazingText algorithm. Many downstream natural language processing (NLP) tasks like sentiment analysis, named entity recognit...
2018-07-30 10:12:41
348
转载 DeepMind提出空间语言集成模型SLIM
选自arXiv，作者：Tiago Ramalho , Tomáš Kociský等，机器之心编译，参与：陈韵竹、路。 前不久，DeepMind 提出生成查询网络 GQN，具备从 2D 画面到 3D 空间的转换能力。近日，DeepMind 基于 GQN 提出一种新模型，可以捕捉空间关系的语义（如 behind、left of 等），其中包含一个基于从场景文本描述来生成场景图像的新型多模态目标...
2018-07-27 14:54:57
235
转载 Differentiable Image Parameterizations
A powerful, under-explored tool for neural network visualizations and art.Authors Affiliations Alexander MordvintsevAffiliationsGoogle AINicola PezzottiGoogle AILudwig SchubertGoogle...
2018-07-27 14:53:26
808
转载 Whats new on arXiv
GPU-based Commonsense Paradigms Reasoning for Real-Time Query Answering and Multimodal Analysis We utilize commonsense knowledge bases to address the problem of real- time multimodal analysis. In par...
2018-07-27 14:42:52
760
转载 Grazing and Calculus Revisited
||One of the great things about writing a blog is the occasional interesting email I receive from some of my readers.Recently I was contact by Trung ‘Average’ Phan, a very talented member of Princeton...
2018-07-27 14:42:27
104
转载 AWS Deep Learning AMIs now include ONNX, enabling model portability across deep learning frameworks
The AWS Deep Learning AMIs (DLAMI) for Ubuntu and Amazon Linux are now pre-installed and fully configured with Open Neural Network Exchange (ONNX), enabling model portability across dee...
2018-07-27 14:41:42
196
转载 Distilled News
New Survey Reveals Businesses Are Bullish on Data Lakes The data lake has long served as a powerful tool for data scientists and data engineers. However, today´s business environment often requires t...
2018-07-27 14:41:18
173
转载 Parsimonious principle vs integration over all uncertainties
tl;dr If you have bad models, bad priors or bad inference choose the simplest possible model. If you have good models, good priors, good inference, use the most elaborate model for predictions. To mak...
2018-07-27 14:40:33
146
转载 ACL 2018 Highlights： Understanding Representations and Evaluation in More Challenging Settings
You are using an outdated browser. Please upgrade your browser to improve your experience.I attended the 56th Annual Meeting of the Association for Computational Linguistics (ACL 2018) According to...
2018-07-27 14:39:58
561
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人