成人英语三级
The more time scientists spend designing computers, the more they wonder at human
brain. Tasks that puzzle the most advanced supercomputer--recognizing a face, reading a handwritten note--are child´ s play. Most important, unlike any ordinary computer, the brain can learn from its mistakes. Researchers have tried for years to program computers to imi-tate the brain´s abilities, but without success. Now a growing number of designers believe they have the answer: if a computer is to work 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 nerve cells or neurons.
Ordinary computers work by following a chainlike sequence of detailed instructions.
Although very fast, their processors can perform only one task at a time. This approach works best in solving problems that can be broken down into simpler logical pieces. The pro-cessors in a neural-network computer,by contrast,form a network much like the nerve :cells in the brain. Since these artificial (人造的) neurons are interconnected, they can share infor-mation and perform tasks at the same time. This two-dimensional approach works best at rec-ognizing patterns.
Instead of programming a neural-network computer to make decisions,its maker trains it to recognize patterns in any solution to a problem by repeatedly feeding examples to the machine.
Neural networks come in all shapes and sizes. Until now most existed as software simu-lations (模拟品) because redesigning computer chips took a lot of time and money. By exper-imenting with different approaches through software rather than hardware, scientists have been able to avoid costly mistakes.
It can be inferred from the first paragraph that a computer__________.
A.can recognize a face
B.cannot learn from its mistakes
C.cannot follow detailed instructions
D.can read a handwritten note
科学家们在设计计算机上所花的时间越多,他们对大脑就越是好奇。象认出人脸,读出手写的便条等使最高级的计算机都头疼的问题,对孩子来说却是很简单的事情。更为重要的是,与普通电脑不同,大脑可以从自身的错误中吸取经验教训。这么多年以来研究者们都在尝试着让计算机来模仿大脑的行为,但是都没有成功。现在越来越多的设计者认为他们找到了答案:要想让电脑工作起来更像大脑而不是一个超级大的计算器,就必须把它做得像大脑一样,能够通过一张很大的相互联系的神经细胞网来传输信息。
普通计算机是按照一系列详细的指令来工作的。虽然电脑工作很快,但是处理器一次只能处理一个问题。这种方法在处理那些能够被分解成更简单的逻辑编码的问题时效果最好。相比之下,神经网络计算机的处理器能够形成一个跟大脑中的神经细胞很相似的网络。
因为这些人造的神经元是相互连接的,他们能够同时分享信息和完成指令。这种两维的方法在模式识别时效果最好。
神经网络计算机的制造者们并没有为其编写做决定的程序,而是通过不断地输入例子,使其在处理问题时能够自己找到解决办法。
神经网络计算机有各种形状和尺寸。直到现在为止,它们大多数只是作为软件模拟品,因为重新设计计算机芯片需要耗费大量的时间和金钱。通过用软件而不是硬件进行各种的实验,科学家们能够避免造成损失重大的错误。
【答案详解】
逻辑推理题。从第一段,Tasks that puzzle the most advanced supercom-puter--recognizing a face,reading,a handwritten note,可以看出认出人脸和读出手写的便条都是最高级的计算机做不了的事情,所以A和D都是错误的。从Most important,unlike any ordinary computer,the brain can learn from its mistakes可以得知,电脑是不能像人脑一样从自己的错误中总结经验教训的,所以B是正确的。从第二段开头这句,Ordinary comput-ers work by following a chainlike sequence of detailed instructions,可以得知,电脑是可以遵循详细的指令的,所以C是错误的。
你可能感兴趣的试题
A.It must be programmed before it works.
B.It can only solve one problem at a time.
C.It is good at solving problems that can be broken down into simpler logical pieces.
D.It is trained to make decisions.
A.its processors act as an interconnected web of neurons
B.it is programmed to make decisions
C.its networks are of all shapes and sizes
D.its neurons are artificial
A.the conventional computer and the neural computer
B.making decisions and recognizing patterns
C.sharing information and performing tasks
D.the computer and the human brain
最新试题
She apologized for __________ the party.
In time of trouble Charlie could always __________ a solutio
The author of this passage is __________ t
The murder rates from 1954 to 1963 and since 1964 in C
The majority of citizens believe that the death penalty is__
Which of the following is NOT an argument by those opposed t
根据下面资料,回答题 With the possible exception of equal rights, per
Directions:You are to write in 100-120 words on the topic Gl
第(85)题选
第(84)题选
