What is AI?

Question 0

What is the problem with defining the AI as a system that thinks like human?

Answer 0

We would have to spend most of our effort on studying how people’s minds operate, rather than thinking about what intelligence pug to mean in various domains.

Question 1

4 definitions of Artificial Intelligence

Answer 1

1. Systems that think like human
2. Systems that act like humans
3. Systems that think rationally
4. Systems that act rationally

Question 2

What is Turing Test?

Answer 2

Operational definition of intelligence behavior.

Question 3

What is wrong with the definition of the AI that is a system that acts like human.

Answer 3

Human often think/act in ways we don’t consider intelligent.

Question 4

Why would you replicate human behavior including its limitations.

Answer 4

The limitation may be useful sometimes. Example : supporting human learning via teachable agents.

Question 5

Rationality

Answer 5

An abstract ideal of intelligence.

Question 6

What is the problem where defining the AI as a system that thinks rationally.

Answer 6

A system that only thinks and doesn’t do anything is quite useless, and it is hard to measure thought.

Question 7

Why using rationality to describe AI is better than using human behavior?

Answer 7

Rationality is more cleanly defined. And because of that:

• it’s a better design objective
• in cases where human behavior is irrational, often we’d prefer rationality.
• once we have rational agent we can always tweak it to become irrational.

Question 8

Why acting rationally is the best description of AI?

Answer 8

Because rationality is better defined than human behavior and action is better defined that thought.

Question 9

Which definition of AI do we use?

Answer 9

The study and design of systems that act rationally.

Question 10

What is an intelligent agent?

Answer 10

Artifacts that act rationally in their environment.

Question 11

What are 4 intelligent agent’s properties?

Answer 11

1) Their actions are appropriate for their goals and circumstances.
2) They are flexible to changing environments and goals/
3) They learn from their expirience.
4) They make appopriate choices given perceprtual limitations and limited resources.

Question 12

What is cognitive plausibility?

Answer 12

A constrain in studying AI that may lead to just replicating human performance instead if understanding the mathematical principles behind the intelligence.

Question 13

What is robot?

Answer 13

An artificial agent that physically present in the world.

Question 14

What is software agent? Give an example.

Answer 14

An agent without a physical presence. Example: text-based tranlation agents, intelligent tutoring system.

Question 15

What is the similiarity between a software agent and a robot?

Answer 15

They share all fundamental components of intelligent behaviour, except for the way they interact with the environment.

Question 16

What are 4 inputs to an intelligent agent?

Answer 16

1) Prior knowledge
2) Past experiences
3) Goals/values
4) Observations

Question 17

What is the output of an intelligent agent?

Answer 17

Actions

Question 18

Representation of the input of an agent?

Answer 18

Knowledge

Question 19

A goal of AI?

Answer 19

Specify how system can:

• Acquire and represent knwoledge about a domain (representation)
• Use the knowledge to solve problems in that domain. (Reasoning)

Question 20

What does a representation and reasoning system contain?

Answer 20

• Representation language

- Computational reasoning procedures

Question 21

What is a R&R system’s pipeline?

Answer 21

problem -> representation -> computation -> representation -> solution

Question 22

What is representation language used for in R&R systems?

Answer 22

It is used to desribe the environment and problems to be solved.

Question 23

What are computational reasoning procedures used for in R&R systems?

Answer 23

They are used to compute a solution to a problem.

Question 24

What is the choice of an appropriate R&R system depends on?

Answer 24

Various dimensions: properties of the environment, type of problems, the agent, the computational resourses.

Question 25

2 kinds of problems?

Answer 25

1) Static

2) Sequential

Question 26

What problem types are ones where finding a solution does not involve reasoning into the future?

Answer 26

Static

Question 27

What problem types are ones where finding a solution does involve reasoning into the future?

Answer 27

Sequential

Question 28

What are fixed and indefinite horizons?

Answer 28

In sequentail problems, fixed horizon means that the problem require reasoning a fixed number of steps into the future.
Indefinite horizon - finate, but unknown number of steps.

Question 29

3 problem types in AI?

Answer 29

1) Constrain Satisfaction (static)
2) Answering Query (static)
3) Planning (sequential)

Question 30

Name the problem type that involves finding state that satisfies set of constrain.

Answer 30

Constrain satisfaction

Question 31

Name the problem type that involves checking if a given proposition true/likely, given what is known.

Answer 31

Answering query

Question 32

Name the problem type that involves finding sequence of actions to reach a goal state/maximize outcome.

Answer 32

Planning

Question 33

Name 2 types of environment.

Answer 33

1) Deterministic

2) Stochastic (Uncertain)

Question 34

What does sensing unsertanty mean?

Answer 34

It means that the agent cannot fully observe the current state of the world.

Question 35

What does effect uncertainty mean?

Answer 35

The agent does not know for sure the effects of it’s actions.

Question 36

How to know if environment is stochastic or deterministic?

Answer 36

An environment is stochastic if at least one of sensing uncertainty or effect uncertainty if true, otherwise it is deterministic.

Question 37

Name 2 representation types.

Answer 37

1) Logic

2) Probability

Question 38

What are explicit state, features, and relations representation schemes?

Answer 38

Explicit state - modeling the environment by enumerating states.
Features - modeling the environment by describing a state in terms of features.
Relations - describing states in terms of objects and relations.

Question 39

Name 2 types of world representations based on the abstraction levels.

Answer 39

1) Flat - single level of abstraction

2) Hierarchical - multiple level of abstraction.

Question 40

What is hierarchical representations are mainly used for?

Answer 40

Scaling up flat representations

Question 41

What is the difference between using knowledge given and knowlledge learned from experience?

Answer 41

When knowledge is given, the agent given a model of the world once and for all. When knowledge learned from experience is used, the agent can learn how the world work based on experience, but it still starts with some prior knowledge.

Question 42

What is the difference when an agent has goals or preferences?

Answer 42

When an agent has a goal, there is some state or set of states that the agent want to be in and there is some proposition or set of propositions that the agent wants to make true.
When an agent has preferences, agent’s task is to reach a state which makes it as happy as possible and how happy the agent is in each state is described ny a preference/utility function.

Question 43

Name 3 kinds of agents that may exist in multi-agent domains.

Answer 43

1) Cooperative
2) Competitive
3) A bit of both

Question 44

Name 5 examples of AI use.

Answer 44

1) Natural language understanding
2) Computer vision
3) Speech recognition
4) Robotics
5) Language generation