Machine Intelligence and Robotics: Report of the NASA Study Group : Final Report |
From inside the book
Results 1-5 of 42
Page 407
And with Learning , efficiency is furthe improved by directing Search in accord with earlier experiences . By ac tually analyzing the situation , using what we call Planning methods , the machine may obtain a really fundamental ...
And with Learning , efficiency is furthe improved by directing Search in accord with earlier experiences . By ac tually analyzing the situation , using what we call Planning methods , the machine may obtain a really fundamental ...
Page 411
It is often supposed that this false - peak problem is the chief obstacle to machine learning by this method . This certainly can be troublesome . But for really difficult problems , it seems to us that usually the more fundamental ...
It is often supposed that this false - peak problem is the chief obstacle to machine learning by this method . This certainly can be troublesome . But for really difficult problems , it seems to us that usually the more fundamental ...
Page 413
III we will consider “ learning ” systems . The behavior of those systems can be made to change in reasonable ways depending on what happened to them in the past . But by themselves , the simple learning systems are useful only in ...
III we will consider “ learning ” systems . The behavior of those systems can be made to change in reasonable ways depending on what happened to them in the past . But by themselves , the simple learning systems are useful only in ...
Page 418
... point of learning . 6 It would indeed be remarkable if this failed to yield properties more useful than would be obtained from completely random sequence selection . The generating problem is discussed further in Minsky ( 1956a ) .
... point of learning . 6 It would indeed be remarkable if this failed to yield properties more useful than would be obtained from completely random sequence selection . The generating problem is discussed further in Minsky ( 1956a ) .
Page 421
Choosing O close to unity means slow , but reliable , learning . 0 is really a sort of memory decay constant , and its choice must be determined by the noise and stability of the environment — much noise requires long averaging times ...
Choosing O close to unity means slow , but reliable , learning . 0 is really a sort of memory decay constant , and its choice must be determined by the noise and stability of the environment — much noise requires long averaging times ...
What people are saying - Write a review
We haven't found any reviews in the usual places.
Other editions - View all
Common terms and phrases
activities analysis applications approach areas Artificial Intelligence automated automatic base become behavior called centers complex computer science concept concerned construction cost described devices direct discussion domain elements engineering environment example existing experience exploration expressions field Figure functions GAME given goal Group heuristic human important increase interest knowledge language learning limited machine intelligence major manipulators mathematical mechanisms memory methods mission NASA nature Newell objects operations organization performance planning position possible present problem solving Proc procedure processing produce Project properties proving psychology reasoning represent representation robot rules selected sequence simple solution space spacecraft specific Stanford step structure Study success symbolic task techniques theorem theory tion understanding Univ University York
Bibliographic information
| Title | Machine Intelligence and Robotics: Report of the NASA Study Group : Final Report |
| Author | NASA Study Group on Machine Intelligence and Robotics |
| Contributor | United States. National Aeronautics and Space Administration |
| Publisher | National Aeronautics and Space Administration, 1980 |
| Original from | Indiana University |
| Digitized | 29 Nov 2012 |
| Length | 400 pages |
| Export Citation | BiBTeX EndNote RefMan |