compiler could execute your kind of perplexing numbers as effectively like they had been a raw sort in the language. [7 marks] 7 Compiler Construction Give a concise portrayal of the rule parts of either Lex and Yacc or the relating Java instruments JLex and Cup. [5 + 5 marks] Illustrate their utilization by framing how you would cultivate a parser for verbalizations produced using identifiers, numbers, unary short and matched supervisors +, , and/. Your parser ought to make a parse tree in a relationship of your decision tending to the clarification that is familiar with it. On the off chance that it helps, you could expect that verbalizations will be done by making a semicolon after them. [10 marks] 3 Prolog for Artificial Intelligence Consider the going with issue to be taken care of utilizing a Prolog program: Given a shut planar polygon tie tended to as a quick overview of n vertices [v(x1,y1), v(x2,y2), . . . , v(xn,yn)] register the region of the encased polygon, and the course of the chain. The district is selected by the line fundamental 1/2 R x dyy dx where the key is over the polygon chain. A nave game-plan is given by the going with structure, which

At this point Pacbaby has been moved once again to the 1970s! Pacbaby has seen that during the 1970s, basically every individual who wears disguises moreover has a mustache, whether the individual being insinuated is Pacman, a phantom, or even a vivacious Ms. Pacman. So Pacbaby reasons that it's the best an entryway for an update from his Innocent Bayes cerebrum: he's getting a tree-extended Naive Bayes mind so that the highlights he sees shouldn't even worry about to be free. In this solicitation, we'll investigate learning and selection in an impression of Pacbaby's new mind. A tree-extended Naive Bayes model (Tanb) is undefined from a Naive Bayes model, with the exception of the highlights are not generally expected to be restrictively free given the class Y . In particular, if (X1, X2, . . . , Xn) are the components tending to the elements that Pacbaby can see, a Tanb awards X1, . . . , Xn to be in a treestructured Bayes net as well as having Y as a parent. The model we investigate is aside. Y X1 X2 X4 X3 X5 X6

In section, we two times have attempted to assist Pacbaby with seeing his dad, Pacman, from phantoms. (a) [1 pt] Suppose we notice no components as confirmation in the Tanb above. What is the social occasion rule for the Tanb? Make the recipe as for the CPTs (Conditional Probability Tables) and earlier probabilities in the Tanb. (b) [2 pts] Assume we see each of the components X1 = x1, X2 = x2, . . . , X6 = x6 in the Tanb above. What is the gathering rule for the Tanb? Structure the condition concerning the CPTs and earlier probabilites in the Tanb. (c) [3 pts] Specify an end request that is valuable for the solicitation P(Y | X5 = x5) in the Tanb over (the request variable Y ought not be incorporated your referencing). The amount of factors that are in the best part (there might be mutiple; expecting this is what is going on, list only one of the best) activated by factor end with your referencing? Which factors might they at some point say they are?

(d) [3 pts] Specify an end request that is skilled for the request P(X3 | X5 = x5) in the Tanb above (counting X3 in your referencing). The amount of factors that are in the best part (there might be mutiple; tolerating this is what is happening, list only one of the best) prompted by factor expulsion with your referencing? Which components might they at some point say they are?

 

(e) [2 pts] Does it take a gander at to run Gibbs dissecting to do assurance in a Tanb? In two or less sentences, legitimize your response. (f) [2 pts] Suppose we are given a dataset of perspective on Y and every one of the factors X1, . . . , X6 in the Tanb above. License C to mean the full scale count of bits of knowledge, C(Y = y) infers how much perspective on the occasion Y = y, C(Y = y, Xi = xi) suggests the count of the times the occasion Y = y, Xi = xi happened, etc. Utilizing the C documentation, make the most unbelievable probability measures for all CPTs including the variable X4. (g) [2 pts] In the documentation of the solicitation above, make the Laplace smoothed checks for all CPTs including the variable X4 .