Introduction to Neural Networks View more

Delve into the inner machinery of neural networks to discover how these flexible learning tools actually work.

Book 15 Lessons

Introduction

Start

Neural Networks

The Computer Vision Problem

The Folly of Computer Programming

Can Computers Learn?

Neurons

The Decision Box

Activation Arithmetic

Decision Boundaries

Building an XOR Gate

Classification

Sigmoid Neurons

Training a Single Neuron

Layers

Hidden Layers

Curve Fitting

Universal Approximator

A Shape-Recognizing Network

Course description

Artificial neural networks learn by detecting patterns in huge amounts of information. Much like your own brain, artificial neural nets are flexible, data-processing machines that make predictions and decisions. In fact, the best ones outperform humans at tasks like chess and cancer diagnoses.

In this course, you'll dissect the internal machinery of artificial neural nets through hands-on experimentation, not hairy mathematics. You'll develop intuition about the kinds of problems they are suited to solve, and by the end you’ll be ready to dive into the algorithms, or build one for yourself.

Topics covered

  • Artificial Intelligence
  • Classification
  • Backpropagation
  • Logic Gates
  • Convolutional Networks
  • Gradient Descent
  • Computer Vision
  • Activation Functions
  • Universal Approximation

Prerequisites and next steps

A basic proficiency with algebra will help you understand this course. Remembering how to get the slope from an equation of a line is enough. Some basic knowledge of logic, like what AND and OR mean would also be useful. You don't need to know how to code to learn a lot from this course.

Prerequisites