Читать книгу The Innovation Ultimatum - Steve Brown - Страница 41

Neural networks underpin most of today's artificial intelligence. They operate quite differently from traditional digital computers. Traditional computers are glorified adding machines. Neural nets are organized more like the highly interconnected structures found in our brains.

Neural nets are made up of connected “nodes,” which act like neurons. Each node holds a numerical value. Unlike binary computers that work with zeros and ones, each node can have a range of values; the range depends on the application. Nodes are arranged into layers. The first layer is known as the input layer and the final layer is known as the output layer. All of the layers in between are known as hidden layers (see Figure 1.1).

Figure 1.1 A simple neural network.

Typically, the more layers there are, and the more nodes in each layer, the more capable the neural network. Neural networks with many layers are known as “deep” neural networks. This is where the term deep learning comes from.

Every node in the hidden layers has both inputs and outputs. Each node is connected to every node in the previous layer and every node in the next layer. The value of each node is influenced by the values of all the nodes it is connected to in the previous layer. Here's the tricky bit: some nodes have a stronger influence on the value of proceeding nodes than others; their influence is weighted. The value of each node is the weighted sum of the values of the previous nodes. These weightings are determined during the training phase and collectively make up what is known as “the model.” The model determines the functionality of the neural network: different weightings, different functionality. Information passes across the network from the input layer to the output layer via this complex web of weighted interconnections.

Neural networks are trained with a process known as backpropagation, or “backprop” as it's known in the business. The details of how backprop works is beyond the scope of this book. At a high level, backprop is a computationally intensive statistical approach that compares the desired output of a neural network with the actual output and then tweaks the weightings in the network to improve the accuracy of results. When the right result is given, the weightings of all the pathways through the neural network that lead to the correct result are strengthened. If the result was incorrect, the pathways that lead to the incorrect result are weakened. Over time, with exposure to more and more data, the model becomes increasingly accurate. The network “learns” the correct complex associations between inputs and outputs.