AI ASSIGNMENT

P101/0949g/19
1 .A
DFS is not guaranteed to find an optimal path; iterative deepening is. DFS may
explore the entire graph before finding the target node; iterative deepening only
does this if the distance between the start and end node is the maximum in the
graph.
B
State Space Tree : It is a tree constructed from all transition of an algorithm or any
design of your code from initial state to final state. Basically it is used for showing
flow of recursive piece of code. Search Space Tree : It is tree (Basically Decision
tree) constructed from which an algorithm searches
C
Top-down Parsing is a parsing technique that first looks at the highest level of the
parse tree and works down the parse tree by using the rules of grammar while
Bottom-up Parsing is a parsing technique that first looks at the lowest level of the
parse tree and works up the parse tree by using the rules of grammar
D

 A Feed-Forward Neural Network is a type of Neural

Network architecture where the connections are "fed forward", i.e. do not
form cycles (like in recurrent nets).
 The term "Feed forward" is also used when you input something at the input
layer and it travels from input to hidden and from hidden to output layer.
The values are "fed forward".

 Backpropagation is a training algorithm consisting of 2 steps: 1) Feed

forward the values 2) calculate the error and propagate it back to the earlier
layers. So to be precise, forward-propagation is part of the
backpropagation algorithm but comes before back-propagating.
 2A. The preposition "for" has many different meanings. Even in the phrase
"are for" it can mean:
o i. "are used for" as above.
o ii. "favors" as in "Cheney is for burning more fossil fuel and against
conserving resources." This can be ruled out by selectional
restrictions: this meaning requires an animate subject, unlike
"hammers".
o iii. "are intended to be given to" as in "The presents are for the baby."
This can be ruled out by selectional restrictions: it requires an animate
object, unlike "driving".
 B. "driving" can mean:
o i. forcing an object to move against resistance, as above.
o ii. driving a car (by far the most frequent meaning).
o iii. impelling a person to undesired behaviors (as in "driving me
crazy", "driving me to drink")
o quite a few other specialized meanings (iv. "driving" in golf, v.
"driving cattle", etc.)

However, most of these can be ruled out by selectional restrictions on the

object. E.g. (ii) requires a car as object; (iii) and (v) require animate objects,
etc.

 C. "nails" can be either the tool or fingernails. However, frequency in the

context of "hammer" gives a preference for the tool.
 D. "into" can mean
o i. motion into the interior of a region, as in "He drove the nail into the
board".
o ii. motion through a boundary into the interior of another region, as
above.
o iii. "in the direction of" as in "He looked into the sun".
o iv. "against" as in "He ran into a brick wall".

Here, I think, one has to rely on world knowledge that a hammer is used to
drive a nail through the surface of an object into its interior.

4
Similarlities

In both finding corresponding points and disparities is the same and they are
area of computer vision

Differences

In technique for dealing with images of a fixed scene by moving camera

information from a continuous sequence can be used while in stereo vision
we are always restricted to two simultaneous frames

In technique for dealing with images of a fixed scene by a camera

dispacements are produced simultaneously while in stereo it is sequetially