O'Reilly logo

Ensemble Machine Learning by Ankit Dixit

Stay ahead with the world's most comprehensive technology and business learning platform.

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, tutorials, and more.

Start Free Trial

No credit card required

Local receptive fields

In the fully connected layers shown earlier, the inputs were depicted as a vertical line of neurons. In a convolutional net, it'll instead help to think of the inputs as a 18×18 square of neurons, whose values correspond to the 18×18 pixel intensities we're using as inputs: 

Figure 10.19: Representation of a digital mage

As usual, we'll connect the input pixels to a layer of hidden neurons, but we won't connect every input pixel to every hidden neuron. Instead, we only make connections in small, localized regions of the input image.

To be more precise, each neuron in the first hidden layer will be connected to a small ...

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, interactive tutorials, and more.

Start Free Trial

No credit card required