The Neural Network Pattern Recognition Tool (nprtool) in MATLAB is a user-friendly GUI for designing and training neural networks for pattern recognition tasks. While ‘nprtool’ itself does not have built-in outlier detection features, you can preprocess your data to detect and handle outliers before importing the data into ‘nprtool’.
For outlier detection you can use functions like ‘isoutlier’, 'filloutliers’ and ‘rmoutliers’, they can be used to detect outliers in data using methods and to replace or remove them from an array or table.
Similarly, for data preprocessing, function like ‘mapminmax’ can be used to normalize and scale data. Function like ‘sequentialfs’ can be used for feature selection to reduce the dimensionality of the data. You can refer to the below documentation for detailed steps available for data preprocessing - https://in.mathworks.com/help/matlab/preprocessing-data.html
For further information, refer to the documentation links below:
- https://in.mathworks.com/help/deeplearning/gs/pattern-recognition-with-a-shallow-neural-network.html
- https://in.mathworks.com/help/matlab/ref/isoutlier.html
- https://in.mathworks.com/help/matlab/ref/filloutliers.html
- https://in.mathworks.com/help/matlab/ref/rmoutliers.html
- https://in.mathworks.com/help/stats/sequentialfs.html
