AI

Question 1

What is Agent?

Answer 1

Agent: A “device” that responds to stimuli from its environment
Sensors
Actuators
Much of the research in artificial intelligence can be viewed in the context of building agents that behave intelligently

Question 2

What is Reflex?

Answer 2

Reflex: actions are predetermined responses to the input data

Question 3

Approaches to Research in Artificial Intelligence

Answer 3

Engineering track
Performance oriented
Theoretical track
Simulation oriented

Question 4

Techniques for Understanding Images

Answer 4

Template matching
Image processing
edge enhancement
region finding
smoothing
Image analysis

Question 5

Language Processing

Answer 5

Syntactic Analysis
Semantic Analysis
Contextual Analysis

Question 6

Components of a Production Systems

Answer 6

Collection of states
Start (or initial) state
Goal state (or states)
2. Collection of productions: rules or moves
Each production may have preconditions
3. Control system: decides which production to apply next

Question 7

State Graph ve Tree nedir?

Answer 7

State Graph: All states and productions
Search Tree: A record of state transitions explored while searching for a goal state
Breadth-first search
Depth-first search

Question 8

Heuristic, Requirements?

Answer 8

Heuristic: A “rule of thumb” for making decisions
Requirements for good heuristics
Must be easier to compute than a complete solution
Must provide a reasonable estimate of proximity to a goal

Question 9

Meta-Reasoning,Closed-World Assumption,Frame problem

Answer 9

Meta Reasoning: the ability of a system evaluate, improve its own thinking process.
Closed World Assumption: in a lack of information system assumes that the information is not present.
Frame Problem: The challenge in AI where a system struggles to adapt changes in environment.

Question 10

AI Learning types?

Answer 10

İmitation: a machine learning model learning by observing and mimicking the behaviour of an expert.
Supervised Training: a machine learning model is trained on a labeled dataset, where each input is associated with corresponding output.
Reinforcement: involves training model to make sequences of decisions by interacting with its environment.

Question 11

Associative memory

Answer 11

Associative memory: memory based on patterns.Getting information that is relevant to the current information.
One direction of research seeks to build associative memory using neural networks that when given a partial pattern, transition themselves to a completed pattern.