This page shows training details of the neural network that is used for recognition of symbols on the main page.
- Test data set size
- 10 %
- Learning rounds
- Batch size
- Max iterations per batch
- Min deriv. comp. max magnitude
- Initialization seed
- Optimization algorithm
- Rprop initial step
- Rprop max step
- Rprop step up mult
- Rprop step down mult
Train set contain images that are used to directly train the neural network.
Images in the Test set are used for evaluation only; the neural network was not trained for them,
thus, they measure how well the network generalizes.
Following image shows the test set which is randomly selected as 10% of input data images.
- Correctly predicted.
- Not correctly predicted but the correct answer was 2nd or 3rd.
- Not correctly predicted.
- Number in the corner
- Confidence (output value of the neuron).