Late 1960s - Early 1970s: Third Generation Computers
One of the most important advances in the development of computer hardware in the late 1960s and early 1970s was the invention of the integrated circuit, a solid-state device containing hundreds of transistors, diodes, and resistors on a tiny silicon chip. It made possible the production of large-scale computers (mainframes) of higher operating speeds, capacity, and reliability at significantly lower costs.
Another type of computer developed at the time was the minicomputer. It profited from the progresses in microelectronics and was considerably smaller than the standard mainframe, but, for instance, powerful enough to control the instruments of an entire scientific laboratory. Furthermore operating systems, that allowed machines to run many different programs at once with a central program that monitored and coordinated the computer's memory, attained widespread use.
|
TEXTBLOCK 1/1 // URL: http://world-information.org/wio/infostructure/100437611663/100438659498
|
|
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
|
|