Community Profile

photo

Kamuran Turksoy


Last seen: mer än ett år ago Active since 2012

Statistics

  • First Review
  • Knowledgeable Level 1
  • Revival Level 1
  • First Answer

View badges

Content Feed

View by

Question


Is it possible to change some properties of only a subset of units (neurons) in a hidden layer?
I am wondering if it is possible to change some properties of only a subset of units (neurons) in a hidden layer? Let say you ha...

ungefär 5 år ago | 1 answer | 0

1

answer

Question


Multi Input Multi Sequence Neural Network
The question is how to define a multi input multi sequence neural network (NN) in Matlab? There is a way to define multi sequ...

mer än 5 år ago | 1 answer | 0

1

answer

Answered
How can I set the normalization of the performance parameter in training a neural network?
net.performParam.normalization does not have an option of 'normalized'. It has three options: 'none' (default: no normaliza...

mer än 5 år ago | 1

| accepted

Question


Why neural network sometimes performs worse when additional input variables are used?
Why neural network sometimes performs worse when additional input variables are used? I would expect a neural network traine...

mer än 5 år ago | 1 answer | 0

1

answer

Question


Selection of Neural Network Training Data
One can divide his/her data into training, validation and testing and use them to train a neural network model (regression in my...

mer än 5 år ago | 1 answer | 0

1

answer

Answered
How to change the performance function of neural network to mean absolute relative error
I found my own answer for the performance function myperf = mse(1-y./t) as follows: net.performFcn='mse'; % this is the defau...

mer än 5 år ago | 0

| accepted

Question


How to change the performance function of neural network to mean absolute relative error
Hello, I know the Matlab NN toolbox has MSE, SSE, MAE and SAE performance functions but would like to implement a custom perf...

nästan 6 år ago | 2 answers | 0

2

answers

Question


Single PLS model based on multiple datasets
Is there any way to train a single PLS model on several training datasets? Let X1, X2 and X3 be the predictive variables mat...

ungefär 6 år ago | 0 answers | 0

0

answers

Answered
Time Series Normalization??
If you have multiple inputs, and the amplitudes of your inputs are different then it is better to normalize your inputs. In othe...

nästan 11 år ago | 0