-
最小二乘曲线拟合
基于Python编写的用于曲线拟合，最小二乘法(Based on Python for curve fitting, least squares method.)
- 2020-11-03 18:29:51下载
- 积分：1
-
Selective Search的Python实现
Selective Search来自于2012年IJCV的文章。其思想是先使用图像分割的方法得到一些初始分割区域(类似于是在图像上生成很多的超像素)，然后利用层次分组的策略(类似于层次聚类)将这些初始区域进行合并，得到的这些区域作为目标定位的候选区域.相对于对候选区域的蛮力搜索， Selective Search大幅度降低了搜索空间, 提高了算法速度。 该版本利用Python实现，安装依赖库后可以直接运行，提取任意图片的Proposals。
- 2022-08-20 19:36:52下载
- 积分：1
-
小波神经网络的时间序列预测代码
说明： 小波神经网络的时间序列预测代码小波神经网络是结合 小波变换理论与人工神经网络的思想而构造的一种新的 神经网络模型，它结合了小波变换良好的时频局域化性质及神经网络的自学习功能，(Time series prediction code of wavelet neural networ
Time series prediction using wavelet process neural network
For example, Ding and Zhong used a wavelet process neural network to solve time series prediction problems)
- 2021-02-08 10:21:41下载
- 积分：1
-
Python K-Means Clustering with Cosine Similarity
pythonweb数据聚类
- 2022-02-24 08:53:32下载
- 积分：1
-
Recommender-Systems-master
使用协同过滤的推荐系统测试代码Predicting movie ratings using collaborative filtering and latent concept extractors based on matrix decomposition methods like SVD and CUR on the movielens-100k dataset
The project explores techniques for predicting unknown user ratings based on a large dataset of users and movie ratings.(Recommender-SystemsWe used 6 different recommender methods to predict user ratings across the data sets.
Namely we set up Collaborative Filtering along with its baseline variant and Matrix decomposition techniques like Singular Value Decomposition and CUR. Moreover, we also implemented dimensionality reduction in these matrix decomposition techniques which preserved 90% of the energy so as to increase the computational efficiency while keeping the accuracy similar for these methods.)
- 2019-01-13 21:30:57下载
- 积分：1
-
用Python进行自然语言处理(中文翻译NLTK)
这本书提供自然语言处理领域非常方便的入门指南。 它可以用来自学， 也可以作为自然
语言处理或计算语言学课程的教科书，或是人工智能、文本挖掘、语料库语言学课程的补充
读物。本书的实践性很强，包括几百个实际可用的例子和分级练习。(This book provides a very convenient entry guide for Natural Language Processing. It can be used for self-study or for nature.
Textbooks for language processing or computational linguistics, or supplements to courses in artificial intelligence, text mining, Corpus Linguistics
Reading. This book is highly practical, including hundreds of practical examples and grading exercises.)
- 2018-11-06 19:30:45下载
- 积分：1
-
HMM-homework
说明： 隐马尔科夫实现，包含forward-hmm, Viterbi-hmm, Baum-Welch-hmm(Hidden Markov implementation, including forward-hmm, Viterbi-hmm, Baum-Welch-hmm)
- 2019-04-26 17:02:43下载
- 积分：1
-
derangementsRecursion
A derangement Recursion written in Python
- 2010-11-02 06:22:16下载
- 积分：1
-
OFDM
基于OFDM的多准则下认知无线电资源分配问题的研究,认知无线电资源分配(Cognitive radio resource allocation problem of OFDM multi-criteria research, cognitive radio resource allocation)
- 2013-11-23 13:11:42下载
- 积分：1
-
tensorflow-fcn-master
说明： 卷积网络正在推动着图像识别方面的进步，其不仅改进了整体图像的分类效果，而且在具有结构化输出的局部任务上也取得了进步，包括边界框目标检测，关键点预测等。
自然下一步是改进在像素级别上的预测。其实，以前的方法已经使用卷积网络进行语义分割任务，其中每个像素都被标记为属于目标或属于其他区域，但让具有缺点。
FCN和CNN的区别：CNN卷积层之后连接的是全连接层；FCN卷积层之后仍连接卷积层，输出的是与输入大小相同的特征图，提出一个端到端，像素对像素的全卷积网络用于语义分割任务(Convolution network is promoting the progress of image recognition. It not only improves the classification effect of the whole image, but also makes progress in the local tasks with structured output, including boundary box target detection, key point prediction and so on.
The natural next step is to improve prediction at the pixel level. In fact, previous methods have used convolutional networks for semantic segmentation tasks, in which each pixel is marked as belonging to the target or other regions, but it has disadvantages.
The difference between FCN and CNN: CNN convolution layer is connected with full connection layer after CNN convolution layer; FCN convolution layer is still connected with convolution layer after FCN convolution layer, and the output is the same as the input size of feature map. An end-to-end, pixel to pixel full convolution network is proposed for semantic segmentation task)
- 2020-09-18 19:48:18下载
- 积分：1
