-
What this book is aboutNeural networks are one of the most beautiful programming paradigms ever invented. In the conventional approach to prog
-
On the exercises and problemsIt's not uncommon for technical books to include an admonition from the author that readers must do the exercises and pr
-
Using neural nets to recognize handwritten digitsThe human visual system is one of the wonders of the world. Consider the following sequence of handwritten digits: img
-
How the backpropagation algorithm worksIn the last chapter we saw how neural networks can learn their weights and biases using the gradient descent algorithm.
-
Improving the way neural networks learnWhen a golf player is first learning to play golf, they usually spend most of their time developing a basic swing. Only
-
A visual proof that neural nets can compute any functionOne of the most striking facts about neural networks is that they can compute any function at all. That is, suppose som
-
Why are deep neural networks hard to train?Imagine you're an engineer who has been asked to design a computer from scratch. One day you're working away in your of
-
Deep learningIn the last chapter we learned that deep neural networks are often much harder to train than shallow neural networks. Th