Hi Aritra,
The error message suggests that the input "P" is not in the expected format. To resolve this issue, you can consider the following steps:
- Ensure that "P" is a Matrix, where each column represents a sample, and each row represents a feature of those samples.
- Ensure that "T" is also a Matrix, where each column represents to a target class of a sample in "P", and each row represent the corresponding one hot encoding of that class.
Here is an example of the "newpnn" function:
% If you have 3 features and 5 samples
P = [
0.1, 0.2, 0.3, 0.4, 0.5;
0.5, 0.4, 0.3, 0.2, 0.1;
0.2, 0.3, 0.4, 0.5, 0.6
];
% If you have 2 classes
% Each column corresponds to the class of the sample in P
T = [
1, 0, 1, 0, 1; % Class 1
0, 1, 0, 1, 0 % Class 2
];
% Create the PNN with a specified spread
spread = 0.438644;
net_1 = newpnn(P, T, spread);
For more information on the "newpnn" function, please refer to the following documentation: https://www.mathworks.com/help/deeplearning/ref/newpnn.html
