Modular Neural Networks - Biological Basis

Biological Basis

As artificial neural network research progresses, it is appropriate that artificial neural networks continue to draw on their biological inspiration and emulate the segmentation and modularization found in the brain. The brain, for example, divides the complex task of visual perception into many subtasks. Within a part of the brain, called the thalamus, lies the lateral geniculate nucleus (LGN) which is divided into different layers that separately process color and contrast: both major components of vision. After the LGN processes each component in parallel, it passes the result to another region to compile the results.

Certainly some tasks that the brain handles, like vision, have a hierarchy of sub-networks. However, it is not clear whether there is some intermediary which ties these separate processes together on a grander scale. Rather, as the tasks grow more abstract, the isolation and compartmentalization breaks down between the modules and they begin to communicate back and forth. At this point, the modular neural network analogy is either incomplete or inadequate.

Read more about this topic:  Modular Neural Networks

Famous quotes containing the words biological and/or basis:

    Much of the ill-tempered railing against women that has characterized the popular writing of the last two years is a half-hearted attempt to find a way back to a more balanced relationship between our biological selves and the world we have built. So women are scolded both for being mothers and for not being mothers, for wanting to eat their cake and have it too, and for not wanting to eat their cake and have it too.
    Margaret Mead (1901–1978)

    Self-alienation is the source of all degradation as well as, on the contrary, the basis of all true elevation. The first step will be a look inward, an isolating contemplation of our self. Whoever remains standing here proceeds only halfway. The second step must be an active look outward, an autonomous, determined observation of the outer world.
    Novalis [Friedrich Von Hardenberg] (1772–1801)