Machine Intelligence and Robotics: Report of the NASA Study Group : Final Report |
From inside the book
Results 6-10 of 56
Page 407
... solution at- tempts . Unfortunately , when we write a straightforward program for such a search , we usually find the resulting process to be enormously inefficient . With Pattern Recognition techniques , efficiency can be greatly ...
... solution at- tempts . Unfortunately , when we write a straightforward program for such a search , we usually find the resulting process to be enormously inefficient . With Pattern Recognition techniques , efficiency can be greatly ...
Page 408
... solution to such a problem , that solution can be found eventually by any blind exhaustive process which searches through all possibilities . And it is usu- ally not difficult to mechanize or program such a search . But for any problem ...
... solution to such a problem , that solution can be found eventually by any blind exhaustive process which searches through all possibilities . And it is usu- ally not difficult to mechanize or program such a search . But for any problem ...
Page 422
... solution , but requires 2 " cells for n properties , which is com- pletely impractical for large systems . What is required is a system which computes some sampling of all the joint conditional probabilities , and uses these to estimate ...
... solution , but requires 2 " cells for n properties , which is com- pletely impractical for large systems . What is required is a system which computes some sampling of all the joint conditional probabilities , and uses these to estimate ...
Page 429
... solution of a problem , then we may encounter " mesa " phenomena which will limit performance on diffi- cult problems . ( See Sec . IC . ) One way to escape this is to have the ma- chine learn to generalize on what the Trainer does ...
... solution of a problem , then we may encounter " mesa " phenomena which will limit performance on diffi- cult problems . ( See Sec . IC . ) One way to escape this is to have the ma- chine learn to generalize on what the Trainer does ...
Page 434
... solution in reasonable time by using reasonably simple and accessible combinations of methods de- veloped in the ... solutions of subproblems . Recently , much effort has been devoted to the construction of training sequences in ...
... solution in reasonable time by using reasonably simple and accessible combinations of methods de- veloped in the ... solutions of subproblems . Recently , much effort has been devoted to the construction of training sequences in ...
Other editions - View all
Common terms and phrases
algorithms Allen Newell analysis applications areas Artificial Intelligence automated base basic behavior Chart chess complex computer science concepts Conf construction DENDRAL domain element engineering example experience Feigenbaum Feldman Figure function GAME generate-and-test goal H. A. Simon heuristic programming heuristic search human hypotheses ill-structured problems inference Information Processing input intelligence and robotics INTERLISP knowledge logic Logic Theorist machine intelligence manipulators mathematical mechanisms Memo memory methods Michie Minsky mission operations MYCIN NASA NASA's Natural Language Newell ORGANISM-1 Papers 3d Intl pattern recognition performance problem solving problem space problem statement Proc procedure Project Project MAC PSYC psychology representation rover rules Semantic sensors sequence Simon simplex method Slagle solution solver spacecraft Stanford Research Institute Stanford Univ structure Study Group symbolic task Tech techniques TEIRESIAS teleoperator theorem proving theory tion variables York