Skip to content

Latest commit

 

History

History
9 lines (6 loc) · 797 Bytes

File metadata and controls

9 lines (6 loc) · 797 Bytes

3D-MNIST-handwritten-digit-classifier

A Deep Learning neural network capable of classifying handwritten digits (0-9) from the MNIST dataset.

This includes a feature for visualising the neural network in 3D which allows the user to see how the neural network is recognising the handwritten digits when extracting patterns.

This also includes a user interface that allows users to draw digits. After that the neural network would classify the drawn digit in real time.

This is accomplished by utilizing a Convolutional Neural Network (CNN) to classify the inputs of handwritten digit images. The hidden layers of the network is composed of convolution layers and pooling layers. This allows the network to extract patterns from the input images in order to detect the digits and classify them.