The more time scientists spend designing computers, the more they marvel at the human brain. Tasks that stump the most advanced supercomputer— 1 a face, reading a handwritten note are child"s play for the 3-Ib. 2 . Most important, unlike any conventional computer, the brain can learn 3 its mistakes. Researchers have tried for years to program computers to 4 the brain"s abilities, but without success. Now a growing number of designers believe they have the answer: if a computer is to 5 more like a person and less like an over-grown calculator, it must be built more like a brain, which distributes information across a vast interconnected web of 6 cells, or neurons.
Conventional computers function by following a chainlike sequence of detailed 7 . Although very fast, their processors can perform only 8 task at a time. This approach works best in solving problems that can be broken down into simpler logical pieces. The processors in a neural-network computer, by contrast, 9 a grid much like the nerve cells in the brain. Since these 10 neurons are interconnected, they can share information and perform tasks at the same time. This two-dimensional approach works best at recognizing patterns.
Instead of 11 a neural-network computer to make decisions, its makers trains it to recognize the patterns in any solution to a problem 12 repeatedly feeding examples to the machine.
Neural-network computers come in all shapes and sizes. 13 now most existed as software simulations because redesigning computer chips 14 a lot of time and money. By experimenting with different approaches through 15 rather than hardware, scientists have been able to avoid costly mistakes.