The Math of Neural Networks

Amazon.com Price: $4.76 (as of 18/04/2019 22:03 PST- Details)

Description

There are lots of reasons why neural networks fascinate us and have captivated headlines in latest years. They make internet searches better, organize photos, and are even used in speech translation. Heck, they may be able to even generate encryption. On the same time, they’re also mysterious and mind-bending: how exactly do they accomplish these things ? What goes on inside a neural network? On a high level, a network learns identical to we do, through trial and error. This is true regardless if the network is supervised, unsupervised, or semi-supervised. Once we dig a bit deeper though, we discover that a handful of mathematical functions play a major role in the trial and error process. It also becomes clear that a seize of the underlying mathematics helps clarify how a network learns. In the following chapters we will be able to unpack the mathematics that drive a neural network. To try this, we will be able to use a feedforward network as our model and follow input as it moves through the network.


Recent Products