HOW CAN I USE 3 DIFFERENT DATA TO TRAIN NEURAL NETWORK

7 次查看（过去 30 天）
JIBIN GEORGE
JIBIN GEORGE 2021-4-12
评论： Srivardhan Gadila 2021-4-15
I am trying to train a neural network with raw data, normalised data and standardised data.But it shows some errors. I need to do this as one after another resulting 3 different neural networks so I can compare the output with the target.
The code I tried is attached below,
%training neural network using raw data
p=x
p
p = p'
t=t'
mynet = feedforwardnet
view(mynet)
train = train(mynet,p,t)
results = sim(mynet,p)
compare = t==results
%training data using standardised data
p1=xs
p1
p1=p'
t1=t'
mynet1 = feedforwardnet
view(mynet1)
train = mynet1(mynet1,p1,t1)
results1 = sim(mynet1,p)
compare1 = t1==results1
%training data using normaised data
p2=xn
p2
p2=p'
t2=t'
mynet2 = feedforwardnet
view(mynet2)
train2 = mynet2(mynet2,p2,t2)
results2 = sim(mynet2,p2)
compare2 = t2==results2
and the error message I hae recieved
>> train = mynet1(mynet1,p1,t1)
Error using network/sim (line 248)
Inputs is not a matrix or cell array.
  3 个评论
显示 1更早的评论
Srivardhan Gadila
Srivardhan Gadila 2021-4-15
@JIBIN GEORGE, can you provide the exact information of the other errors you are getting apart from the ones mentioned in the question.

请先登录，再进行评论。

请先登录，再回答此问题。

回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Deep Learning Toolbox 的更多信息

标签

产品

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by