Swipe to navigate through the chapters of this book
Neural networks are networks of nerve cells in the brains of humans and animals. The human brain has about 100 billion nerve cells. We humans owe our intelligence and our ability to learn various motor skills and intellectual capabilities to the brain’s complex relays and adaptivity. The nerve cells and their connections are responsible for awareness, associations, thoughts, consciousness and the ability to learn. Mathematical models of neural networks and their implementation on computers are nowadays used in many applications such as pattern recognition or robot learning. The power of this fascinating bionics branch of AI is demonstrated on some popular network models applied to various tasks.
Please log in to get access to this content
To get access to this content you need the following product:
Bionics is concerned with unlocking the “discoveries of living nature” and its innovative conversion into technology [Wik13].
Even the author was taken up by this wave, which carried him from physics into AI in 1987.
For a clear differentiation between training data and other values of a neuron, in the following discussion we will refer to the query vector as q and the desired response as t (target).
Support vector machines are not neural networks. Due to their historical development and mathematical relationship to linear networks, however, they are discussed here.
A data point is contradictory if it belongs to both classes.
Visual representations of such edge features, including explanation, can be found at deeplearning.stanford.edu.
Accessed April, 2016.
- Neural Networks
- Springer International Publishing
- Sequence number
- Chapter number
- Chapter 9