Artificial Intelligence |
Dentro del libro
Resultados 1-3 de 13
Página 489
Processing elements , or units , are always in one of two states , active or inactive
. In the figure , units colored black are active and units colored white are inactive .
Units are connected to each other with weighted , symmetric connections .
Processing elements , or units , are always in one of two states , active or inactive
. In the figure , units colored black are active and units colored white are inactive .
Units are connected to each other with weighted , symmetric connections .
Página 512
Increase the weights on connections between the active output unit and active
input units . This makes it more likely that the output unit will be active next time
the pattern is repeated . One problem with this algorithm is that one output unit
may ...
Increase the weights on connections between the active output unit and active
input units . This makes it more likely that the output unit will be active next time
the pattern is repeated . One problem with this algorithm is that one output unit
may ...
Página 521
A unit becomes active if any object is located within its receptive field . There is a
unit associated with each zone — the zone is called the unit ' s receptive field . ! 4
Whenever an object is located in a unit ' s receptive field , the unit becomes ...
A unit becomes active if any object is located within its receptive field . There is a
unit associated with each zone — the zone is called the unit ' s receptive field . ! 4
Whenever an object is located in a unit ' s receptive field , the unit becomes ...
Comentarios de la gente - Escribir un comentario
Crítica de los usuarios - Marcar como inadecuado
very good
Contenido
Problems Problem Spaces and Search | 29 |
7 | 61 |
Knowledge Representation Issues | 105 |
Derechos de autor | |
Otras 11 secciones no mostradas
Otras ediciones - Ver todas
Términos y frases comunes
active addition agents algorithm allow answer apply approach assertions becomes belief build called Chapter choose clauses combined complete concept consider consistent constraints contains corresponding define dependency described discussed domain elements example fact Figure function given goal heuristic important initial input instance interpretation John kinds knowledge knowledge base labeled language learning logic look match meaning methods move natural necessary node object occur operators output particular path perform position possible predicate present problem procedure produce properties question reasoning relation represent representation result robot rules semantic sentence shown in Figure shows simple single situation slot solution solve space specific statements step stored structure Suppose task techniques things tree true understanding units usually variables weights