Convolutional neural networks.
In my
introductory post
on neural networks, I introduced the concept of a neural
network that looked something like this.
As it turns out, there are
many different neural network architectures
, each with its
own set of benefits. The architecture is defined by the type of layers we implement
and how layers are connected together. The neural network above is known as
a
feed-forward network
(also known as a multilayer perceptron) where we simply
have a series of fully-connected layers.
Today, I'll be talking about
convolutional neural networks
which are used
heavily in image recognition applications of machine learning. Convolutional
neural networks provide an advantage over feed-forward networks because they
are capable of considering locality of features.
Consider the case where we'd like to build an neural network that could recognize
handwritten digits. For example, given the following 4 by 4 pixel image as input,
our neural network should classify it as a "1".