Artificial neural networks session
You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
Gerardo Marx Chávez-Campos f66a70fee5 development 1 year ago
Readme.md initial commit 1 year ago
main.ipynb development 1 year ago
mnist_test.csv initial commit 1 year ago
mnist_train.csv initial commit 1 year ago

Readme.md

Introduction

The present session will introduce the Python classes and how to create your own Artificial Neural Network (ANN) class. The class will implement the __init__, feedforward, and backpropagation methods.

Each method will be described in detail to understand the ANNs inner work. Then, the handwriting MNIST dataset will be used to train and test our ANN.

Objectives

  • Learn the basics of using Python Classes
  • Create methods for: create, feedforward, and backpropagation
  • Train the ANN
  • Test the ANN

Pending tasks (Your work)

  • Create a Python function to evaluate the ANNs performance by passing all the test images(mnist_test.csv) and compare the target with the ANNs results.
  • Make a plot of the ANNs evolution performance for at least 10 combinations of the number of hidden nodes, learning rate, and the number of epochs.