Channel: Sebastian Lague

Category: Education

Tags: pythonfeedforwardaimnistnumpymachine learningclassificationneural networkartificial intelligence

Description: In this episode we look at how neural networks can be represented with matrices, and create a simple feedforward network in python. Note: at 2:31 the second bias vector should only have two rows, not three. Code: github.com/SebLague/Neural-Network-python I owe a lot to this excellent online book on neural networks: neuralnetworksanddeeplearning.com Learn more about weight initialization: cs231n.github.io/neural-networks-2/#init (note: numpy.random.randn and numpy.random.standard_normal are functionally equivalent, the latter just takes a tuple for the shape parameter). Support the creation of more tutorials: patreon.com/SebastianLague paypal.me/SebastianLague