Overview
-
Take a deep dive into the inner workings of neural networks by learning how to create one from scratch in Python.
Syllabus
-
Introduction
- Creating a neural network in Python
- What you should know
- Using GitHub for the exercise files
- What is a neural network?
- Why Python?
- The many applications of machine learning
- Types of classifiers
- Types of neural networks
- Multilayer perceptrons
- Neurons and the brain
- A simple model of a neuron
- Activation functions
- Perceptrons: A better model of a neuron
- Challenge: Finish the perceptron
- Solution: Finish the perceptron
- Logic gates
- Challenge: Logic gates with perceptrons
- Solution: Logic gates with perceptrons
- Linear separability
- Writing the multilayer perceptron class
- Challenge: Finish the multilayer perceptron class
- Solution: Finish the multilayer perceptron class
- The need for training
- The training process
- The error function
- Gradient descent
- The delta rule
- The backpropagation algorithm
- Challenge: Write your own backpropagation method
- Solution: Write your own backpropagation method
- Segment display recognition
- Challenge: Design your own SDR neural network
- Solution: Design your own SDR neural network
- Challenge: Train your own SDR neural network
- Solution: Train your own SDR neural network
- Next steps
