Machine Intelligence and Robotics: Report of the NASA Study Group : Final Report |
From inside the book
Results 1-5 of 46
Page 357
... statements to display internal values and intermediate results , many more programming aids are available in an interactive laboratory environment . Changes to programs are automatically marked on reformatted listings , the author and ...
... statements to display internal values and intermediate results , many more programming aids are available in an interactive laboratory environment . Changes to programs are automatically marked on reformatted listings , the author and ...
Page 379
... statements within the program . Deducing the cause of a failure from the debug evidence produced is a purely manual operation . Changes are made by keypunching new cards and manually merging the corrections with the program . Then the ...
... statements within the program . Deducing the cause of a failure from the debug evidence produced is a purely manual operation . Changes are made by keypunching new cards and manually merging the corrections with the program . Then the ...
Page 380
... statement of a finished design or implementation . The formulation of these finished products is addressed only by a set of management guidelines . As one can imagine , these manual processes with only minimal guidelines , unevenly ...
... statement of a finished design or implementation . The formulation of these finished products is addressed only by a set of management guidelines . As one can imagine , these manual processes with only minimal guidelines , unevenly ...
Page 385
... statement of the type , " If object 1 is to the left of object 2 and object 2 is to the left of object 3 , then object 1 is to the left of object 3. " Complex knowledge base systems may also have to interface with sophisticated ...
... statement of the type , " If object 1 is to the left of object 2 and object 2 is to the left of object 3 , then object 1 is to the left of object 3. " Complex knowledge base systems may also have to interface with sophisticated ...
Page 423
... statement about the rela- tions among them . Thus we say of Fig . 7a , “ A rectangle ( 1 ) contains two subfigures disposed horizontally . The part on the left is a rectangle ( 2 ) which contains two subfigures disposed vertically ; the ...
... statement about the rela- tions among them . Thus we say of Fig . 7a , “ A rectangle ( 1 ) contains two subfigures disposed horizontally . The part on the left is a rectangle ( 2 ) which contains two subfigures disposed vertically ; the ...
Other editions - View all
Common terms and phrases
algorithms Allen Newell analysis applications areas Artificial Intelligence automated base basic behavior capabilities centers chess complex computer science computer systems concept Conf construction cost DENDRAL devices discussion domain elements engineering environment example existing experience exploration Feigenbaum Figure functions GAME goal hardware heuristic programming heuristic search human hypotheses ill-structured problems inference information processing input intelligence and robotics interaction knowledge learning logic machine intelligence Man-Machine Systems manipulators Marvin Minsky mathematical mechanisms memory ment methods Minsky mission operations MYCIN NASA NASA's Natural Language Newell Papers 3d Intl pattern recognition performance planetary planning problem solving problem space problem statement Proc procedure processor Project Project MAC PSYC psychology representation rover rules sensors sequence Simon simplex method solution solver spacecraft specific Stanford Research Institute Stanford Univ structure Study Group subproblems symbolic task Tech techniques TEIRESIAS teleoperator theory tion
Popular passages
Page 442 - Generally speaking, a successful division will reduce the search time not by a mere fraction, but by a. fractional exponent. In a graph with 10 branches descending from each node, a 20-step search might involve 1020 trials, which is out of the question, while the insertion of just four lemmas or sequential subgoals might reduce the search to only 5 X 104 trials, which is within reason for machine exploration. Thus, it will be worth a relatively enormous effort to find such islands in the solution...
Page 447 - Samuel (19606) has taken a strong position against the idea of machines thinking. His argument, based on the fact that reliable computers do only that which they are instructed to do, has a basic flaw; it does not follow that the programmer therefore has full knowledge (and therefore full responsibility and credit for) what will ensue. For certainly the programmer may set up an evolutionary system whose limitations are for him unclear and possibly incomprehensible.
Page 406 - I believe that it is; that we are on the threshold of an era that will be strongly influenced, and quite possibly dominated, by intelligent problem-solving machines. But our purpose is not to guess about what the future may bring; it is only to try to describe and explain what seem now to be our first steps toward the construction of "artificial intelligence.
Page 432 - It is extremely doubtful whether there is enough information in "win lose, or draw" when referred to the whole play of the game to permit any learning at all over available time scales.... For learning to take place, each play of the game must yield much more information. This is... achieved by breaking the problem into components. The unit of success is the goal. If a goal is achieved, its subgoals are reinforced; if not they are inhibited. (Actually, what is reinforced is the transformation rule...
Page 433 - In changing just one instruction at a time the machine had not taken large enough steps in its search through program space. The second paper goes on to discuss a sequence of modifications in the program generator and its reinforcement operators. With these, and with some "priming" (starting the machine off on the right track with some useful instructions), the system came to be only a little worse than chance. Friedberg et al. (1959) conclude that with these improvements "the generally superior...
Page 339 - Robotics The problem of controlling the physical actions of a mobile robot might not seem to require much intelligence. Even small children are able to navigate successfully through their environment and to manipulate items, such as light switches, toy blocks, eating utensils, etc. However these same tasks, performed almost unconsciously by humans, when performed by a machine require many of the same abilities used in solving more intellectually demanding problems. Research on robots or robotics...
Page 443 - C,, be the name of that method (or a list of such methods). If there is no such method the corresponding entry is null. Now suppose that there is no entry for...
Page 435 - The solution, by machine, of really complex problems will require a variety of administration facilities. During the course of solving a problem, one becomes involved with a large assembly of interrelated subproblems. From these, at each stage, a very few must be chosen for investigation. This decision must be based on 1) estimates of relative difficulties and 2) estimates of centrality of the different candidates for attention. Following subproblem selection (for which several heuristic methods...
Page 406 - Introduction A visitor to our planet might be puzzled about the role of computers in our technology. On the one hand, he would read and hear all about wonderful "mechanical brains" baffling their creators with prodigious intellectual performance. And he (or it) would be warned that these machines must be restrained, lest they overwhelm us by might, persuasion, or even by the revelation of truths too terrible to be borne. On the other hand, our visitor would find the machines being denounced, on all...
Page 418 - A,A,C, which can have more than two values. and the sequences are therefore [by definition] not significant. Let it discard these and pick some others. Sooner or later, however, some sequences will prove significant; that is, their distribution functions will peak up somewhere. What the machine does now is to build up new sequences like the significant ones. This is the important point. If it merely chose sequences at random it might take a very long while indeed to find the best sequences. But with...