Вы находитесь на странице: 1из 27

Conceptual Dependency

Conceptual Dependency
• CD is a Theory of how to represent the kind of
Knowledge about events that is usually
contained in natural language sentence. The
Goal is to represent the Knowledge in a way
that
• 1.Facilitates drawing Inferences From the
Sentences.
• 2.is Independent of the language in which the
sentence were originally stated.
Simple CD Representation
The Conceptual Dependency having some symbols
• ->Arrow indicate direction of the Dependency.
• <-> it indicates two way Link between Actor and
Action.
• P indicates Past tense.
• ATRANS is one of primitive acts used by the
theory.it indicates transfer of possession.
• O indicates object case relation.
• R indicates Recipient Case Relation.
Four Primitive Conceptual Categories
P-past
f-future
T-transition
Tf- Finished Transition
ts-start Transition
K-Continuing
?-interrogative
/-Negative
Nil-Present
Delta-Timeless
C-Conditional
“John ate the egg”
Script
• A Script is a Structure that describe
Stereotyped sequence of events in a particular
context. A Script Consists of a set of slots.
Components of a script
• 1.Entry Conditions
• 2.Result
• 3.Props
• 4.roles
• 5.Track
• 6.Scenes
• Entry Conditions : Conditions that must, in
general,be satisfied before the events
described in the script can occur.
• Result: Conditions that will, in general ,be true
after the events described in the script have
occurred.
• Props: slots representing objects that are
involved in the event described in the script.
• Roles: Slots representing people who are in
the event described in the script.
• Track: the specific variation on a more general
pattern that is represented by this particular
script.
• Scenes: the actual sequence of a events that
occur.
Unit -IV
Connectionist Models
Hopfield Networks
• Hopfield network has the following interesting
features
• Hopfield Network have processing or units are
always in one of two states ,active or inactive.
• In the Fig unit Colored Black are active and
unit colored white are inactive.
• Units are connected to each other with
weighted ,symmetric connections.
• A Positively weighted connection indicates
that two units tend to activate each other.
• A negative connection allows an active unit to
deactivate a neighbor unit.
• If any of its neighbors are active, the units
computes the sum of the weights on the
connections to those active neighbors.
• If the sum is positive the unit becomes active,
otherwise it becomes inactive.
Perceptron
• The Perceptron an invention of Rosen belt
(1962),was one of the earliest neural network
models.
• A Perceptron model a neuron by taking a
weighted sum of its inputs and sending the
output 1 if the sum is greater than some
adjustable threshold value.
• The inputs (x1,x2….xn) and connection weights
(w1,w2,….wn)in the figure both positive and
negative.
Neuron
perceptron
Perceptron with adjustable threshold
implemented as additional weight
• If the presence of some feature xi tends to
cause the perceptron to fire ,the weight wi will
be positive.
• If the feature xi inhibits the perceptron the wi
will be negative.
• The perceptron itself consists of the
weights,summation processor and adjustable
threshold processor.
• Learning is a process of modifying the values
of weights, and threshold.
• Perceptron computes a binary function of its
input.
• Several perceptron's can be combined to
compute more complex functions.

Вам также может понравиться