The example codes above are related to a 5-layer MLP NN (Input layer - 3 hidden layer - Output layer) classification for the problem of recognizing numbers from 0 to 9.
For this issue, the dataset available in the link below has been used. https://www.kaggle.com/competitions/digit-recognizer/data (Also available in Dataset folder)
Run the main.py file to run the code. After running the code, you will need to specify the following.
- The dataset path
- If you want to use a previously saved model, the path to the saved model must be specified
- The number of iteration steps (Epochs)
- Data validation percentage
- Test set percentage
- Learning rate
- Batch size
- Optimizer model
- The number of neurons in the first layer
- The number of neurons in the second layer
- The number of neurons in the third layer