In this lesson, we will discuss machine learning and neural networks. We will learn about the overall topic of artificial intelligence (AI), with machine learning (ML) being a subset of AI. Neural networks are then a subset of machine learning. Neural networks are a technique where a computer network performs a task without human intervention and trains and improves over time. Applications are in artificial general intelligence, finance, speech recognition, image recognition, self driving cars, and more. We will discuss the networks weights and biases and learn how a real neural network operates and how it is trained.

More Lessons: http://www.MathAndScience.com
Twitter: https://twitter.com/JasonGibsonMath

00:00:00 Introduction
00:01:23 Applications of Machine Learning
00:10:40 Difference Between AI, ML, & NNs
00:15:36 NNs Inspired by the Brain
00:20:38 What is a Model?
00:25:34 Training Methods
00:31:38 Neural Network Architecture
00:39:22 Input and Output Layers
00:48:00 Neuron Connections
00:57:08 Review of Functions
01:05:52 Neuron Weights and Biases
01:09:37 Writing Neuron Equations
01:19:34 Equations in Matrix Form
01:31:33 How to Train NNs?
01:37:00 The Loss Function