Load Dataset
Once you complete the data preparation
- Click the folder icon and select the data file (.csv format) to import the dataset
ANNHUB will use a small data sample to visualize how it looks
Configure neural network
- After the dataset is loaded, click Configure Neural Network to continue.
Note: ANNHUB will auto-suggest the neural network type and parameters based on the imported dataset.
You can still adjust the configuration to achieve the best result.
- Click Create Neural Network to save your configuration
- Click Train Neural Network to continue.
Train neural network
Once the Neural Network is configured, it is ready to be trained to learn features from the dataset.
Note: ANNHUB will auto-suggest the training parameter in this step as well.
You can still adjust the configuration to achieve the best result.
Evaluate neural network
ANNHUB provides many evaluation techniques that help users evaluate the trained model.
For pattern recognition application
ANNHUB supports Confusion Matrix and ROC curve techniques to evaluate the trained model.
The Confusion Matrix for training, validation, and test datasets is presented in great detail.
Valuable information such as the total number of samples in a specific class is correctly identified and how many samples are miss-classified.
This information is summarized in the Accuracy, Sensitivity, and Specificity columns.
For function approximation/fitting application
ANNHUB supports the Regression curve that presents how well the predicted outputs approximate their targets.
The Regression curves for training, validation, and test dataset are all available.
Note: If the Bayesian Regularization training algorithm is selected, the evaluation information
for the validation set will not be displayed as that dataset is not required.
Test the trained neural network with unknown data (optional)
After evaluation, the neural network can still be tested to ensure it can cope with an entirely new dataset.
Depending on your Neural Network application, appropriate evaluation techniques will be used.
Note: You can import the .cvs file or manually test the model
Test pattern recognition model
Test function fitting/ prediction model
Export neural network for deployment
- Click on Export Neural Network
- Select Export Options and click Export
Note: A typical approach to AI is always trial and error, so training with different datasets
and parameters are recommended to find the best model.