搜索资源列表
-
0下载:
使用决策树,支持向量机以及人工神经网络完成对MNIST手写数字体的分类。-Using a decision tree, support vector machines and artificial neural network to classify the number of MNIST handwritten font.
-
-
0下载:
该库的目标是提供一种易于使用的方法来训练和测试神经网络的MNIST数字(在浏览器或node.js中)。它包括10000个不同的mnist数字样本,通过建立这个以便与Synaptic开箱即用。可以通过MNIST数字加载器自由创建不同示例c的任何数字(从1到60 000)(The goal of the library is to provide an easy-to-use method to train and test the MNIST numbers of the neural netwo
-
-
0下载:
用cnn卷积神经网络实现对mnist手写库的识别(mnist classfication with convolution neural network)
-
-
0下载:
简单的手写数字识别,在深度神经网络中的简单尝试,对于初学者有个很好的理解(Simple handwritten numeral recognition, in the depth of neural network simple attempt, for beginners have a good understanding)
-
-
0下载:
CNN-mnist自制算法,使用卷积神经网络进行计算,准确率99.2(CNN-mnist is a algorithm written by yourself.A convolution neural network is used for calculation, the accuracy rate is 99.2)
-
-
2下载:
使用TensorFlow实现稀疏自编码神经网络,采用数据mnist(Using TensorFlow to realize sparse atuoencoder neural network, using data MNIST)
-
-
0下载:
变分自编码结构,用一个mnist数据。。。。。。(Using TensorFlow to realize Variational Auto-Encoder neural network, using data MNIST)
-
-
2下载:
用Python3实现BP神经网络对MNIST数字手写体识别,下载就能用(Using Python3 to implement BP neural network for MNIST digital handwriting recognition, download can be used)
-
-
0下载:
经典五层卷积神经网络,应用在mnist库上(The classical five layer convolution neural network application in the MNIST database)
-
-
0下载:
实现了在Mnist上的分类,使用了卷积神经网络(use convoluntional neural network to implement classificaiton on Minist.)
-
-
0下载:
基于两层BP神经网络,加入dropout和softmax,输出层使用softmax,实现对手写字符库MNIST的识别,正确率达90%。(Based on the two level BP neural network, adding dropout and softmax, the output layer uses softmax to realize the recognition of handwritten character library MNIST, the accuracy ra
-
-
1下载:
基本的dnn,准确率有百分之93左右,有注释(Basic DNN, the accuracy rate is ninety-three percent)
-
-
0下载:
带drop out 的mnist 的dnn ,准确率百分之90(The DNN of MNIST with drop out has an accuracy rate of ninety percent)
-
-
0下载:
改进的dnn,准确率达到了百分之95,有注释(Improved DNN, the accuracy rate reached ninety-five percent)
-