@SebastianLague
  @SebastianLague
Sebastian Lague | Neural Networks | E02: predictions (unfinished series) @SebastianLague | Uploaded 6 years ago | Updated 4 days ago
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:
https://github.com/SebLague/Neural-Network-python

I owe a lot to this excellent online book on neural networks:
http://neuralnetworksanddeeplearning.com/

Learn more about weight initialization:
http://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:
https://www.patreon.com/SebastianLague
https://www.paypal.me/SebastianLague
Neural Networks | E02: predictions (unfinished series)Coding Adventure: Compute ShadersCoding Adventure: Optimizing a Ray Tracer (by building a BVH)Coding Adventure: Ray MarchingCoding Adventure: Atmosphere[Unity] Procedural Planets (E04: multiple noise filters)How Do Computers Remember?[Unity] Procedural Planets (E02 settings editor)Coding Adventure: Marching Cubes[Ludum Dare #43] The Resistance: Behind the ScenesI Ran a Chess Programming Tournament, Heres How it Went![Unity] Procedural Planets (E06: simple biomes)

Neural Networks | E02: predictions (unfinished series) @SebastianLague