Artificial IntelligenceMcGraw-Hill, 1991 - 621 páginas A revision of an established text for undergraduate and postgraduate Artificial Intelligence courses, this text incorporates the latest research and methods. |
Dentro del libro
Resultados 1-3 de 29
Página 504
... units . The weights connected to the output units can be adjusted in order to reduce those errors . We can then use the error estimates of the output units to derive error estimates for the units in the hidden layers . Finally , errors ...
... units . The weights connected to the output units can be adjusted in order to reduce those errors . We can then use the error estimates of the output units to derive error estimates for the units in the hidden layers . Finally , errors ...
Página 518
Elaine Rich, Kevin Knight. State Units Plan Units Hidden Units Output Units Figure 18.22 : A Jordan Network of muscles ) , but we need more ... Units Articulatory Units Hidden Plan Units Units Target Units 518 CHAPTER 18. CONNECTIONIST ...
Elaine Rich, Kevin Knight. State Units Plan Units Hidden Units Output Units Figure 18.22 : A Jordan Network of muscles ) , but we need more ... Units Articulatory Units Hidden Plan Units Units Target Units 518 CHAPTER 18. CONNECTIONIST ...
Página 521
... units ? The localist approach is to maintain an array of sixty - four units , one unit for every possible location ( see Figure 18.24 ) . A more efficient approach would be to use a group of eight units for the x - axis and another ...
... units ? The localist approach is to maintain an array of sixty - four units , one unit for every possible location ( see Figure 18.24 ) . A more efficient approach would be to use a group of eight units for the x - axis and another ...
Contenido
What Is Artificial Intelligence? | 3 |
5 | 24 |
Heuristic Search Techniques | 63 |
Derechos de autor | |
Otras 25 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 example fact 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 ON(C operators output parsing particular path perceptron perform players possible preconditions predicate logic problem problem-solving procedure produce PROLOG 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