- What is Artificial Intelligence?
Artificial Intelligence is the field of computer science that highlights the construction of intelligent machine that performs and reacts like individuals.
- What is an artificial intelligence Neural Networks?
Artificial intelligence Neural Networks are composed of multiple nodes, which imitate biological neurons of human brain, empowering the machine to think and learn the same way the human’s do- making them fit for seeing things like speech, objects and animals like we do.
- What are the various areas where AI (Artificial Intelligence) can be used?
Artificial Intelligence can be used in several areas like Computing, Bio-informatics, Speech recognition, Humanoid robot, Space, Computer software and Aeronautics’s etc.
- What is Prolog in AI?
Prolog in AI is a programming language based on logic.
- Give an explanation on the difference between strong AI and weak AI?
Strong AI: It makes solid claims that computers can be made to think on a level equivalent to humans
Weak AI: It predicts that some features that resemble to human intelligence can be united to computer to make it more useful tools.
- Mention the difference between statistical AI and Classical AI?
Statistical AI: It is concerned with “inductive” thought like given a set of pattern, induce the trend etc.
Classical AI: It is more concerned with “deductive” thought given as a set of constraints, deduce a conclusion etc.
- What is alternate, artificial, compound and natural key?
Alternate Key: All candidate keys are known as Alternate Keys except primary keys
Artificial Key: If no key either stands alone, then the last resort is to, simply create a key, by assigning a number to each record. This is known as artificial key.
Compound Key: When there is no single data element that exclusively defines the existence within a construct, then integrating various elements to create a unique identifier for the construct is known as Compound Key.
Natural Key: Natural key is one of the data elements that is stored within a construct and is used as the primary key.
- Which is the best way to go for Game playing problem?
Heuristic approach is the best way to go for game playing issue, as it will use the method based on intelligent guesswork. For e.g. Chess between humans and computers as it will use brute force computation, looking at hundreds of thousands of positions.
- What is agent in artificial intelligence?
Anything identifies its environment with the use of sensors and acts upon an environment by effectors are known as Agent. Agent includes Programs, Robots and Humans etc.
- What does Partial order or planning involve?
In partial order, rather than searching over possible situation it includes searching over the space of possible plans. The idea is to construct a plan piece by piece.
- What are the two different kinds of steps that we can take in constructing a plan?
- Add an operator (action)
- Add an ordering constraint between operators
- What is Neural Network in Artificial Intelligence?
In artificial intelligence, neural network is an emulation of a biological neural system, which receives the data, processes the data and gives the output based on the algorithm and empirical data.
- When an algorithm is considered completed?
An algorithm is completed when it dismisses with a solution when one exists.
- What is a heuristic function?
A heuristic function ranks alternatives, in search algorithms, at each branching step based on the available information to decide which branch to follow.
- What is “Generality” in AI?
Generality is the amount of ease with which the method can be modified to various domains of application.
- What is a top-down parser?
A top-down parser begins by guessing a sentence and logically predicting lower level constituents until individual pre-terminal symbols are made.
- Mention the difference between breadth first search and best first search in artificial intelligence?
These are the two strategies which are quite similar.
Best first search: In this we expand the nodes in accordance with the evaluation function.
Breadth first search: In this a node is expanded in accordance to the cost function of the parent node.
- What are frames and scripts in “Artificial Intelligence”?
Frames are a modified of semantic networks which is one of the popular ways of presenting non-procedural knowledge in an expert system. These are used to share knowledge into substructure by representing “stereotyped situations’.
Scripts are similar to frames, except the values that fill the slots must be ordered. These are used in natural language understanding systems to establish a knowledge base in terms of the situation that the system should understand.
- What does the language of FOPL consists of
- A set of constant symbols
- A set of predicate symbols
- A set of variables
- The logical connective
- A set of function symbols
- A special binary relation of equality
- The Universal Quantifier and Existential Qualifier
- In ‘Artificial Intelligence’ where you can use the Bayes rules?
In Artificial Intelligence, Bayes rule can be used to answer the queries conditioned on one piece of evidence.
- For building a Bayes model how many terms are required?
Three terms are required for building a Bayes model in AI. They are one conditional probability and two unconditional probabilities.
- While creating Bayesian Network what is the consequence between a node and its predecessors?
While creating Bayesian Network, the consequence between a node and its predecessors is that a node can be conditionally independent of its predecessors.
- To answer any query how the Bayesian network can be used?
If a Bayesian Network is a representative of the joint distribution, then by summing all the relevant joint entries, it can solve any query.
- What combines inductive methods with the power of first order representations?
Inductive logic programming combines inductive methods with the power of first order representations.
- In Inductive Logic Programming what needed to be satisfied?
The motto of an Inductive Logic Programming is to come up with the bunch of sentences for the hypothesis such that the entailment constraint is satisfied.