Living Prototypes: The Key to New TechnologyDirectorate of Advanced Systems Technology, Wright Air Development Division, Air Research and Development Command, U.S. Air Force, 1961 - Всего страниц: 499 |
Результаты поиска по книге
Результаты 1 – 5 из 24
Стр. 94
... coding procedure is followed , but the multiple - line automaton has the following structure : f ( x1 , x2 ) . x2 Figure 2 Thus each " neuron " receives inputs from all lines in both bundles . We shall not enter into an analysis of ...
... coding procedure is followed , but the multiple - line automaton has the following structure : f ( x1 , x2 ) . x2 Figure 2 Thus each " neuron " receives inputs from all lines in both bundles . We shall not enter into an analysis of ...
Стр. 95
... coding theorem may be stated as follows : 7 If , for a communication system , there exists a certain maximum rate for transmission of information , the channel capacity C , then for transmission rates R less than C , it is possible to ...
... coding theorem may be stated as follows : 7 If , for a communication system , there exists a certain maximum rate for transmission of information , the channel capacity C , then for transmission rates R less than C , it is possible to ...
Стр. 96
... coding is no better than the iterative coding of von Neumann and McCulloch et al . On the basis of this result , Elias hypothesized that the computa- tional capacity is zero . Petersen carried through a similar argument for binary group ...
... coding is no better than the iterative coding of von Neumann and McCulloch et al . On the basis of this result , Elias hypothesized that the computa- tional capacity is zero . Petersen carried through a similar argument for binary group ...
Стр. 105
... CODING FOR THE COMPUTATION CHANNEL We now return to the question of coding for the computation channel , and our approach is based on certain implications of the noisy coding theorem for transmission channels . The whole process of ...
... CODING FOR THE COMPUTATION CHANNEL We now return to the question of coding for the computation channel , and our approach is based on certain implications of the noisy coding theorem for transmission channels . The whole process of ...
Стр. 107
... redundancy may only be introduced into either 10Xz , or f , or both . At any rate , the coding scheme that we obtain , in general , is X1 α1 F dz decoder encoder و noise Figure 15 INI We write F for the ad hoc function , to 107.
... redundancy may only be introduced into either 10Xz , or f , or both . At any rate , the coding scheme that we obtain , in general , is X1 α1 F dz decoder encoder و noise Figure 15 INI We write F for the ad hoc function , to 107.
Часто встречающиеся слова и выражения
automata basilar membrane behavior binary biological Bionics Boolian brain cells F circuit coding complex components consider contains a jot corresponding curve device discussed dual spaces electronic elements equation example experiment experimental fibers Figure filter formal neuron frequency gain human Information Theory input configuration input lines Integral Geometry intelligence lattice learning light intensity linear logical function loop machine many-valued logical mathematical matrix McCulloch measure mechanism modules nerve nets noise Nyquist stability criterion obtained open-loop organ oscillations output panel parameters pattern recognition Perceptron performed photocell polypheck possible Probabilistic Logics probability vector problem properties pupil area pupil system pupil unrest random redundancy reliability represented response retina scheme servomechanism Sheffer stroke shown signal simple space stability map Symposium theorem theory threshold operator tion transfer function triplet network V₁ variables vector Venn diagram
Популярные отрывки
Стр. 83 - This work was supported in part by the US Army (Signal Corps), the US Air Force (Office of Scientific Research, Air Research and Development Command), and the US Navy (Office of Naval Research); and in part by the National Science Foundation.
Стр. 13 - -to quote his own words " against the ultimate development of mechanical consciousness, in the fact of machines possessing little consciousness now. A mollusc has not much consciousness. Reflect upon the extraordinary advance which machines have made during the last few hundred years, and note how slowly the animal and vegetable kingdoms are advancing. The more highly organized machines are creatures not so much of yesterday, as of the last five...
Стр. 13 - A bird is an instrument working according to mathematical law, which instrument it is within the capacity of man to reproduce with all its movements, but not with a corresponding degree of strength, though it is deficient only in the power of maintaining equilibrium. We may therefore say that such an instrument constructed by man is lacking in nothing except the life of the bird, and this life must needs be supplied from that of man.
Стр. 15 - The human memory is a filing system that has a far greater capacity than that of the largest thinking machine built. A mechanical brain that had as many tubes or relays as the human brain has nerve cells (some ten billion) would not fit into the Empire State Building, and would require the entire output of Niagara Falls to supply the power and the Niagara River to cool it.
Стр. 16 - Instead, observe that thinking is a continuum, an n-dimensional continuum. This notion is certainly not new, for it has existed since man first compared his mental abilities with another man's, and it is implicit in all of the positive arguments on machine intelligence. Psychologists long ago developed "intelligence quotient...
Стр. 14 - A computer is not a giant brain, in spite of what some of the Sunday supplements and science fiction writers would have you believe. It is a remarkably fast and phenomenally accurate moron" (Andree, 1958). 5, The Argument by False Attribution Typical of this type of argument is the following: The Manchester machine which was set to solve chess problems presumably proceeded by this method, namely by reviewing all the possible consequences of all possible moves. This, incidentally, reveals...
Стр. 33 - Before closing, a comment on the question "when?" It is one thing to say it is possible to push machine capabilities way out in the continuum of intelligence, but it is another thing to say when. It was over four hundred years from da Vinci to the Wright brothers. But the sands of time in the scientific world have been flowing much more rapidly of late. Advances now made in a decade compare with earlier steps which took a century. Few would have believed in 1950 that man would hit the moon with a...
Стр. 21 - ... sins of the positivists." Exaggerated claims of accomplishments, particularly from the publicity departments of computer manufacturers, have resulted in such a strong reaction within the scientific community that many swing too far in the opposite direction. Da Vinci and Flying At this point allow me to paraphrase the quotation of da Vinci's, with which this paper was begun, and also, with the benefit of hindsight, expand on it somewhat. Thus, he might have said: When men understood the natural...
Стр. 38 - The Next Advance in Operations Research, Journal of the Operations Research Society of America, Vol 6, no.
Стр. 461 - The MIT systems of automatic coding: Comprehensive, summer session, and algebraic,