what is the purpose of each line of this code?
1 次查看(过去 30 天)
显示 更早的评论
This is a code for training Neural Network:
function [net]=createff(Iin,Target)
net = newff(Iin, Target, 10, {'logsig' 'logsig'}, 'trainscg');
net.trainParam.perf = 'sse';
net.trainParam.epochs = 500;
net.trainParam.goal = 1e-5;
net.trainParam.lr=0.15;
net.trainParam.mc=0.8;
net = init(net);
net = train(net, Iin, Target);
end
Please help me to understand this code.
1 个评论
Greg Heath
2013-7-1
1. delete the net = init statement because newff is self-initializing.
2. Before using a code specifying various parameter values that overwrite default values, it is probably worth your while to try using as many defaults as possible. See the examples in
help newff
doc newff
采纳的回答
Matthew Eicholtz
2013-6-29
The first line creates a feed-forward backpropagation network. Type this in the command window to learn more:
help newff
- '10' is the size of the hidden layer
- 'logsig' is log sigmoid transfer function
- 'trainscg' is scaled conjugate gradient backpropagation
- 'sse' is sum of squared errors
- 'epochs' refers to how many times to run through the training and validation sets
- 'goal' is the stopping criterion
- 'lr' is the learning rate
- 'mc' is the momentum constant
The last two lines initialize and train the network.
help init
help train
0 个评论
更多回答(0 个)
另请参阅
类别
在 Help Center 和 File Exchange 中查找有关 Sequence and Numeric Feature Data Workflows 的更多信息
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!