AI/ML engineer and a talented technical writer who authors 4 scientific books and more than 80 articles and tutorials. https://www.linkedin.com/in/ahmedfgad
In this tutorial we use Cython to reduce the execution time of the genetic algorithm implemented in Python. We've brought down our computational time from 1.46 seconds to a mere 0.08 seconds, so that 1 million generations run in less than 10 seconds with Cython, compared to 180 seconds in Python.
Here we see how to speed up NumPy array processing using Cython. By explicitly declaring the "ndarray" data type, your array processing can be 1250x faster.
Python might be one of today's most popular languages, but it's definitely not the most efficient. See how Cython can easily boost your Python scripts.
In this tutorial, we extend our implementation of gradient descent to work with a single hidden layer with any number of neurons.
In the third part of this series, the implementation of Part 2 will be extended for allowing the GD algorithm to work with a single hidden layer with 2 neurons.
This is the second tutorial in the series which discusses extending the implementation for allowing the GD algorithm to work with any number of inputs in the input layer.
In this tutorial, which is the Part 1 of the series, we are going to make a worm start by implementing the GD for just a specific ANN architecture in which there is an input layer with 1 input and an output layer with 1 output.
