搜索资源列表
yongfenjishenjingwangluoxuexijiqirendedonglixueted
- 摘要:给出了解决机器人控制问题一种神经网络方法。使用一个分级神经网络(NN)结构学习刚体机器人动力学特点。对于一般类别的机械手,使用前训练一系列的三层前馈网络模块,然后把这些基函数实时地用于第四层。使用线性控制原理,辅以非线性补偿控制机械手,使学得的机械手动力学知识创建一个在整个工程中高速控制机械手的控制器。模拟结果表明控制器的性能得到了大大提高。-Abstract: This paper presents a solution to the issue of robot control neu
psobp
- 该文件是使用粒子群算法来求解BP神经网络饿最优解,进而对样本数据训练学习-The document is the use of particle swarm optimization to solving hunger BP neural network the optimal solution, and then the training sample data for the study
7-4
- 归一化LMS算法,自适应滤波研究中的一个小程序。20次训练学习。-Normalized LMS algorithm, Adaptive Filtering in a small program. 20 training and learning.
47821364121
- 根据果蝇优化算法得到极速学习机隐层神经元的数目依据得到的隐层神经元数目和极限学习机的方法对训练样本和测试样本进行训练学习。-According to the fruit flies optimization algorithm to get extreme learning machine based on the number of hidden layer neurons of hidden layer neurons number and extreme learning machine
2-rain
- 基于深度学习神经网络模型,对降雨量进行训练和预测(Rainfall prediction based on depth learning)
bp2
- 用MATLAB 实现对不同种类的饮料或者果汁的分类,通过训练学习,再进行预测,可以得到分类的正确率(The classification of different kinds of drinks or fruit juice is realized by MATLAB, and the correct rate of classification can be obtained by training, learning and forecasting)
encode-xunlian(1)r
- 从给定的很多张自然图片中截取出大小为8*8的小patches图片共10000张,现在需要用sparse autoencoder的方法训练出一个隐含层网络所学习到的特征。该网络共有3层,输入层是64个节点,隐含层是25个节点,输出层当然也是64个节点了。这里只是上传了训练的部分代码,后续继续(A total of 10000 small patches pictures with size 8*8 are extracted from a lot of natural pictures. Now
纯C-CNN
- 纯C深度学习库,里面包含MNIST手写数字识别数据集,编译就能训练和预测(Pure C depth learning library, which contains MNIST handwritten digital recognition data sets, compiling can be trained and predicted.)
学习程序样例
- 演示模型便展示了一学习算法的训练结果,它非常生动地、系统地复现了生物神经网络的活动。(The demonstration model shows the training results of a learning algorithm, which vividly and systematically recombines the activities of the biological neural network.)
机器学习实战
- 讲解机器学习,用个大案例进行学习分心,包括代码编写,训练,模型建立,模型使用方法(Explain machine learning, use a large case for learning distractions, including code writing, training, model building, and model use)
deepdesc-release-master
- 利用深度学习对特征描述符进行训练,得到较精确的特征描述符(The feature descr iptors are trained by depth learning to obtain more accurate feature descr iptors)
Tools-master
- 制作训练数据的python文件,用于深度学习的训练(Python file for making training data)
多任务深度学习改进版
- 这个程序实现了多任务的深度学习,可以提高训练的收敛速度(Multi-task deep learning)
Residual_Neural_Network-master
- 实现了残差神经网的训练,在jubernotebook上运行(The training of residual neural network is realized and it runs on jubernotebook)
基于极限学习机的预测
- 针对非线性预测问题,建立极限学习机的预测模型,将数据样本分为训练样本和测试样本,并采用误差指标进行评价。(Aiming at the problem of non-linear prediction, the prediction model of extreme learning machine is established. The data samples are divided into training samples and test samples, and the error i
基于极限学习机ELM的数据分类
- 针对数据分类问题,提出了基于极限学习机的分类方法,将数据样本分为训练样本和测试样本,并采用准确率指标进行评价。(Aiming at the problem of data classification, a classification method based on extreme learning machine is proposed. The data samples are divided into training samples and test samples, and the
基于深度学习的二进制代码漏洞检测系统
- 二进制代码漏洞检测是一个重要的研究问题。针对当前基于静态分析的二进制代码漏洞检测系统普遍存在误报率高,检测粒度粗,且依赖专家经验等问题,提出了用库/API函数调用程序切片细粒度表示二进制程序,并引入深度学习技术,自动检测二进制程序中库/API函数调用相关漏洞,设计并实现了一个基于深度学习的二进制代码漏洞检测系统——BVDetector。该系统通过对二进制程序进行控制流和数据流分析,从程序中提取库/API函数调用的程序切片,并为程序切片添加有无漏洞的标签;然后将程序切片转换成符合漏洞检测深度学习模
Broad-Learning-System-master
- 宽度学习python实现,有关增加映射节点、增强节点的宽度模型以及增加数据的训练模型实现(Broad-Learning System By Python)
UCI(55个)
- 机器学习训练的数据集-UCI数据集,包含55个数据集(Machine learning training data set -UCI data set, containing 55 data sets)
MNIST_data
- MNIST数据集是机器学习领域中非常经典的一个数据集,由60000个训练样本和10000个测试样本组成,每个样本都是一张28 * 28像素的灰度手写数字图片。(The MNIST data set is a very classic data set in the field of machine learning. It consists of 60,000 training samples and 10,000 test samples. Each sample is a 28 * 28 p