Architecture
The basic architecture consists of three types of neuron layers: input, hidden, and output. In feed-forward networks, the signal flow is from input to output units, strictly in a feed-forward direction. The data processing can extend over multiple layers of units, but no feedback connections are present. Recurrent networks contain feedback connections. Contrary to feed-forward networks, the dynamical properties of the network are important. In some cases, the activation values of the units undergo a relaxation process such that the network will evolve to a stable state in which these activations do not change anymore.
In other applications, the changes of the activation values of the output neurons are significant, such that the dynamical behavior constitutes the output of the network. Other neural network architectures include adaptive resonance theory maps and competitive networks.
Read more about this topic: Neural Network
Famous quotes containing the word architecture:
“Polarized light showed the secret architecture of bodies; and when the second-sight of the mind is opened, now one color or form or gesture, and now another, has a pungency, as if a more interior ray had been emitted, disclosing its deep holdings in the frame of things.”
—Ralph Waldo Emerson (1803–1882)
“Poetry is not only dream and vision; it is the skeleton architecture of our lives. It lays the foundations for a future of change, a bridge across our fears of what has never been before.”
—Audre Lorde (1934–1992)
“All architecture is great architecture after sunset; perhaps architecture is really a nocturnal art, like the art of fireworks.”
—Gilbert Keith Chesterton (1874–1936)