edRVFL
所属分类：人工智能/神经网络/深度学习
开发工具：matlab
文件大小：5KB
下载次数：0
上传日期：2020-05-07 16:04:24
上 传 者：
GHao
说明： 输入：
trainX训练数据
训练标签
testX测试数据
测试标签
模型参数模型参数
输出：
测试准确度
训练时间
测试时间
模型训练模型
(Inputs:
trainX Training data
trainY Training labels
testX Testing data
testY Testing labels
ModelParameters Model parameters
Outputs:
TestAcc Testing Accuracy
TrainingTime Time taken for training
TestingTime Time taken for testing
Model Trained model)
文件列表:
ComputeAcc.m (403, 2018-12-23)
l2_weights.m (164, 2018-12-20)
MRVFL.m (406, 2020-04-02)
MRVFLpredict.m (1565, 2020-04-05)
MRVFLtrain.m (2145, 2020-04-05)
OneVAllEncode.m (373, 2020-04-05)
relu.m (76, 2019-07-19)
sigmoid.m (1646, 2019-02-24)
TEST_edRVFL.m (3155, 2020-04-05)
# Ensemble Deep Random Vector Functional Link (edRVFL)
This set of codes implements Ensemble Deep Random Vector Functional Link (edRVFL) algorithm to classify data.
You should do some research on your own to understand the basic priciples on how edRVFL Works.
To get started, you should refer to 'TEST_RVFL.m'.
#### Parameters
L: Number of layers (Needs to be positive integer)
N: Number of neurons (Needs to be positive integer)
C: Regularisation parameter (Needs to be positive float)
scale: Scale of randomisation (Needs to be positive float)
Activation: Activation function (Shown below)
#### Activation Function
On this set of codes, we implemented edRVFL with 'sigmoid' or 'relu' activation function.
If you wish to try with different activation function, you can replace the following codes in BOTH files (MRVFLtrain.m and MRVFLpredict.m):
"""
% Activation function
switch lower(act_fun)
case "relu"
A1 = relu(A1);
case "sigmoid"
A1 = sigmoid(A1);
otherwise
error("Not Implemented");
end
"""
#### Usage
The main function to train and test Ensemble Deep Random Vector Functional Link is:
"""
[Model,TrainAcc,TestAcc,TrainingTime,TestingTime] = MRVFL(trainX,trainY,testX,testY,ModelParameters);
"""
Inputs:
trainX Training data
trainY Training labels
testX Testing data
testY Testing labels
ModelParameters Model parameters
Outputs:
Model Trained model
TrainAcc Training Accuracy
TestAcc Testing Accuracy
TrainingTime Time taken for training
TestingTime Time taken for testing
近期下载者：
相关文件：
收藏者：