联合开发网   搜索   要求与建议
                登陆    注册
排序按匹配   按投票   按下载次数   按上传日期
按分类查找All 特征抽取(11) 
按平台查找All Jupyter Notebook(11) 

[特征抽取] FeatureExtraction-BAH24

一个从高分辨率卫星图像中提取和识别高压塔、风车、变电站、砖窑和农场堤岸等特征的平台。
a platform to extract and identify features such as high tension towers, windmills, electric substations, brick kilns, and farm bunds from high-resolution satellite imagery. (2024-09-20, Jupyter Notebook, 0KB, 下载0次)

http://www.pudn.com/Download/item/id/1726790911479206.html

[特征抽取] Dual-Convolutional-Malware-Network-DCMN

在我们的工作中,我们提出了一种使用双深度卷积神经网络(DCNN)进行恶意软件分类的新方法。我们的方法利用预先训练的ResNet-50和自定义卷积神经网络来增强特征提取和提高分类性能。
In our work, we presented a novel approach for malware classification using a dual deep convolutional neural network (DCNN). Our method leverages both pre-trained ResNet-50 and a custom convolutional neural network to enhance feature extraction and improve classification performance. (2024-08-01, Jupyter Notebook, 0KB, 下载0次)

http://www.pudn.com/Download/item/id/1722466846217555.html

[特征抽取] NeuroGait

该存储库包含用于使用步态分析检测帕金森病的代码和资源。该项目将用于特征提取的卷积神经网络(CNN)与用于分类的XGBoost相结合,实现了91%的检测精度。采用可解释的人工智能技术来解释模型的预测。
This repository contains code and resources for detecting Parkinson s disease using gait analysis. The project combines Convolutional Neural Networks (CNN) for feature extraction with XGBoost for classification, achieving a detection accuracy of 91%. Explainable AI techniques, are employed to interpret the model s predictions. (2024-07-06, Jupyter Notebook, 0KB, 下载0次)

http://www.pudn.com/Download/item/id/1720239376623512.html

[特征抽取] Text-classification-and-multi-task-model

使用TF-IDF和神经网络对文本进行分类,使用单分类头和双分类头模型。
Classify text using TF-IDF and neural network, employing both single classification head and dual classification heads models. (2024-01-25, Jupyter Notebook, 0KB, 下载0次)

http://www.pudn.com/Download/item/id/1706252990732190.html

[特征抽取] BBC-News-Cluster-Analysis

分析并将BBC 2004-2005年的新闻文章分为五个主题类别:商业、娱乐、政治、体育和科技使用...,
Analyze and cluster BBC news articles from 2004-2005 into five topical categories: business, entertainment, politics, sport, and tech using MiniBatchKMeans and TF-IDF features. (2023-10-10, Jupyter Notebook, 0KB, 下载0次)

http://www.pudn.com/Download/item/id/1697069489584657.html

[特征抽取] Exploratory-Data-Analysis

单变量双变量分析,特征提取,数学运算。
Univariate Bivariate Analysis , feature extraction , mathematical operations. (2020-08-20, Jupyter Notebook, 6KB, 下载0次)

http://www.pudn.com/Download/item/id/1686271893431475.html

[特征抽取] Movie-Prediction

与电影元数据合作预测收入更高的电影,分析数据以检测...
Worked with Movies Meta Data to predict movies with higher revenue, analyzed the data to detect relationships between different variables impacting movie revenue. ?? (2022-03-03, Jupyter Notebook, 841KB, 下载0次)

http://www.pudn.com/Download/item/id/1646263517214933.html

[特征抽取] tartu-nlp-workshop

塔尔图大学为期两天的语料库语言学和主题建模研讨会人文数字方法和...
A two-day corpus linguistics and topic modelling workshop for the University of Tartu Digital Methods in Humanities and Social Sciences Summer School on 22-23 August 2018. (2018-08-23, Jupyter Notebook, 1400KB, 下载0次)

http://www.pudn.com/Download/item/id/1535003315254255.html

[特征抽取] word2vec

实现word2vec,并应用于金庸全集进行研究
Implement word2vec and apply it to the research of Jin Yong s Complete Works (2020-01-29, Jupyter Notebook, 40698KB, 下载0次)

http://www.pudn.com/Download/item/id/1580245623434031.html

[特征抽取] word_vectors_moby_dick

使用Word2Verc和Google合作进行文本分析
Text analysis with Word2Vec and Google Colaboratory (2019-04-12, Jupyter Notebook, 213KB, 下载0次)

http://www.pudn.com/Download/item/id/1555038894631328.html

[特征抽取] Article-Summarizer-and-Classifier

...类别,即商业、娱乐、政治、体育和科技。使用这种方法,我们能够找到...
Article classification and summarization have a genuinely backhanded connection as article classification fall into classification issues rather than summarization, where it is treated as an issue of semantics. A significant piece of the summarization procedure is the recognition of the point or subjects that are examined in an irregular (2020-08-04, Jupyter Notebook, 5247KB, 下载0次)

http://www.pudn.com/Download/item/id/1596514234207339.html
总计:11