3 Introduction to neural prediction: forward propagation 21
Step 1: Predict 22
A simple neural network making a prediction 24
What is a neural network? 25
What does this neural network do? 26
Making a prediction with multiple inputs 28
Multiple inputs: What does this neural network do? 30
Multiple inputs: Complete runnable code 35
Making a prediction with multiple outputs 36
Predicting with multiple inputs and outputs 38
Multiple inputs and outputs: How does it work? 40
Predicting on predictions 42
A quick primer on NumPy 44
Summary 46
4 Introduction to neural learning: gradient descent 47
Predict, compare, and learn 48
Compare 48
Learn 49
Compare: Does your network make good predictions? 50
Why measure error? 51
What’s the simplest form of neural learning? 52
Hot and cold learning 54
Characteristics of hot and cold learning 55
Calculating both direction and amount from error 56
One iteration of gradient descent 58
Learning is just reducing error 60
Let’s watch several steps of learning 62
Why does this work? What is weight_delta, really? 64
Tunnel vision on one concept 66
A box with rods poking out of it 67
Derivatives: Take two 68
What you really need to know 69
What you don’t really need to know 69
How to use a derivative to learn 70
Look familiar? 71
评论1