4000 - 1000 B.C. 4th millennium B.C. In Sumer writing is invented. Writing and calculating came into being at about the same time. The first pictographs carved into clay tablets were used for administrative purposes. As an instrument for the administrative bodies of early empires, which began to rely on the collection, storage, processing and transmission of data, the skill of writing was restricted to only very few. Being more or less separated tasks, writing and calculating converge in today's computers. Letters are invented so that we might be able to converse even with the absent, says Saint Augustine. The invention of writing made it possible to transmit and store information. No longer the ear predominates; face-to-face communication becomes more and more obsolete for administration and bureaucracy. Standardization and centralization become the constituents of high culture and vast empires as Sumer and China. 3200 B.C. In Sumer the seal is invented. About 3000 B.C. In Egypt papyrus scrolls and hieroglyphs are used. About 1350 B.C. In Assyria the cuneiform script is invented. 1200 B.C. According to Aeschylus, the conquest of the town of Troy was transmitted via torch signals. About 1100 B.C. Egyptians use homing pigeons to deliver military information.

TEXTBLOCK 1/1 // URL: http://world-information.org/wio/infostructure/100437611796/100438659725

Neural network A bottom-up artificial intelligence approach, a neural network is a network of many very simple processors ("units" or "neurons"), each possibly having a (small amount of) local memory. The units are connected by unidirectional communication channels ("connections"), which carry numeric data. The units operate only on their local data and on the inputs they receive via the connections. A neural network is a processing device, either an algorithm, or actual hardware, whose design was inspired by the design and functioning of animal brains and components thereof. Most neural networks have some sort of "training" rule whereby the weights of connections are adjusted on the basis of presented patterns. In other words, neural networks "learn" from examples and exhibit some structural capability for generalization.

INDEXCARD, 1/1