A small neural network with only 38 + 12 hidden neurons which has been trained to read handwritten digits has been loaded on this page. It has an error rate of 1.71% on the MNIST dataset.
Please draw a digit with your mouse or with your finger on the canvas! In the table with the digits you will see how this network classifies what you draw.
Please check out all parts in this series describing a neural network from scratch. Both theory and with practical examples as well as a complete Java implementation:
- Part 1 – Foundation.
- Part 2 – Gradient descent and backpropagation.
- Part 3 – Implementation in Java.
- Part 4 – Better, faster, stronger.
- Part 5 – Training the network to read handwritten digits.
- Extra 1 – Data augmentation.
- Extra 2 – A MNIST playground. (This)