Artificial IntelligenceMcGraw-Hill, 1991 - 621 páginas |
Dentro del libro
Resultados 1-3 de 13
Página 489
... active unit to deactivate a neighboring unit . The network operates as follows . A random unit is chosen . If any of its neighbors are active , the unit computes the sum of the weights on the connections to those active neighbors . If ...
... active unit to deactivate a neighboring unit . The network operates as follows . A random unit is chosen . If any of its neighbors are active , the unit computes the sum of the weights on the connections to those active neighbors . If ...
Página 512
... active . 4. 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 ...
... active . 4. 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 ...
Página 521
... 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.14 Whenever an object is located in a unit's receptive field , the unit becomes active ...
... 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.14 Whenever an object is located in a unit's receptive field , the unit becomes active ...
Contenido
5 | 24 |
Heuristic Search Techniques | 63 |
Knowledge Representation Issues | 105 |
Derechos de autor | |
Otras 28 secciones no mostradas
Otras ediciones - Ver todas
Términos y frases comunes
Abbott agents algorithm answer apply approach ARMEMPTY assertions attributes axioms backpropagation backtracking backward belief best-first search breadth-first search Caesar called Chapter chess clauses complete concept conceptual dependency consider constraints contains contradiction corresponding define depth-first depth-first search described discussed domain fact frame function game tree goal grammar graph heuristic Horn clauses important inference inheritance input instance interpretation isa links John justification knowledge base knowledge representation labeled learning Marcus match minimax move MYCIN natural language node object ON(B operators output parsing particular path perceptron perform players possible preconditions predicate logic problem problem-solving procedure produce PROLOG properties represent result robot rules script Section semantic semantic net sentence shown in Figure simple slot solution solve specific step structure Suppose syntactic task techniques theorem things tree truth maintenance system understanding variables version space