neural_network

neural_network, a Python code which illustrates the use of neural networks for deep learning, using back propagation and stochastic gradient descent, by Catherine Higham and Desmond Higham.

Licensing:

The information on this web page is distributed under the MIT license.

Languages:

neural_network is available in a MATLAB version and an Octave version and a Python version.

Related Data and Programs:

pytorch_test, a Python code which tests certain features of pytorch(), a library used for deep learning research.

Author:

Original MATLAB version by Catherine Higham, Desmond Higham; This version by John Burkardt.

Reference:

1. Catherine Higham, Desmond Higham,
   Deep Learning: An introduction for applied mathematicians,
   SIAM Review,
   Volume 61, Number 4, pages 860-891,
   November 2019.

Source Code:

• neural_network.py, the source code.
• neural_network.sh, runs the code.
• neural_network.txt, the output file.

• neural_network.png, a plot of the cost decrease over the iteration.