WebGL MNIST learning

We have transcoded a simple neuron network learning MNIST dataset from python to WebGL. We use our WGLMatrix library to process all linear algebra computations.

The full learning may take a few tens of minutes.

Controls :

The whole dataset may be too large for you graphic card memory. If it overflows, the WebGL context is killed. You need to refresh this webpage and to try again with a reduced version of the dataset.

Network hyperparameters :

SIGMOID
fully connected


Learning parameters :

50000
10000
30
8
3.0


Monitoring :


Logging console :

References :