Lecture 1-Intro to AI Flashcards

1
Q

What are 3 recent breakthroughs in AI?

A

-Speech Recognition & Machine Translation –>2010+
-Image Recognition & Computer Vision–>2012+
-Natural Language Processing–>2014+

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What are the two approaches to AI?

A

-Engineering approach
-Cognitive approach

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What is the engineering approach?

A

-Tries to find optimal solutions
-No matter how–> not necessarily what human do

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

What is the cognitive approach?

A

-Tries to understand the process
-Tries to reproduce human behavior EVEN IF WRONG RESULT

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

What are the 4 points of view?

A

Cognitive:
-Behavior-> act like humans
-Reasoning->think like humans
Engineering:
-Behavior-> act intelligently
-Reasoning->think intelligently

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

What is considered weak AI(3)?

A

-System whose capabilities are not intended to match or exceed those of human beings.
-CAN demonstrate intelligence, BUT no need for mind or consciousness
-SMALL APPLICATION WITH SMALL PURPOSE

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What is considered a strong AI(4)?

A

-used in science fiction
-System that matches or exceeds human intelligence
-SHOULD HAVE consciousness, sentiments, etc.
-GENERAL PURPOSE CAPABLE OF SEVERAL TASKS

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

What are 4 types of agents?

A

-Intelligent Agent Continuum
-A Simple Reflex Agent
-More Sophisticated Reflex Agent
-Learning Agent

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

Name 3 characteristics of the intelligent agent continuum?

A

-Agents receive percepts from environment
-Agent performs actions
-Each agent performs a function to map percept sequences to actions

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Name 3 characteristics of the more sophisticated reflex agent?

A

-A bit smarter than simple-reflex version
-Has the ability to internally model the outside world
-Not at the mercy of what can at the moment be directly sensed

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

Name 3 characteristics of the learning agent?

A

-sense the environment
-criticize with a standard in mind
-provide feedback to update learning elements

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

What is the Turing test?

A

-It measures the intelligence of a computer vs a human
-If a human interrogator cannot tell the computer and human apart, then the computer is intelligent

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

What are 4 examples of capabilities required to pass the Turing test?

A
  • TO COMMUNICATE: Natural Language processing(NLP)
    -SHARE KNOWLEDGE: Knowledge representation
    -STORE KNOWLEDGE: Automated reasoning
    -Machine learning
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

What are arguments FOR the turing test(3)?

A

-Objective notion of intelligence
-Prevents us from arguments about the computer’s consciousness
-Eliminates bias in favor of humans

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

What are arguments AGAINST the turing test(2)?

A

-Not reproducible
-Not constructive

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

What does CAPTCHA stand for?

A

Completely Automated Public Turing test to tell Computers and Humans Apart

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

What does the CAPTCHA do?

A

-System asks a user to complete a test which the computer is able to generate and grade, but not able to solve.
-Because computers are unable to solve the CAPTCHA, any user entering a correct solution is presumed to be human.

18
Q

Why is the CAPTCHA known as reverse turing test?

A

-its given by a machine and targeted to a human and not the opposite like the turing test

19
Q

What are 3 concrete tasks examples of the Modern Bot Evaluation Frameworks?

A

1.Natural Language Understanding(NLU): understanding + processing human language
2..Creative Tasks: AI’s ability to generate creative content
3.Decision-Making Skills: AI’s effectiveness in scenarios requiring complex decision-making

20
Q

What are 3 metrics examples of the Modern Bot Evaluation Frameworks?

A

1.Accuracy and precision: measure of correctness in outputs
2.Response time: speed at which AI provides responses
3.Robustness and generalization: ability to handle unexpected inputs or scenarios

21
Q

What do we do in AI(8)?

A

-Knowledge representation (formal logic)
-Search (especially heuristic search)
-Planning
-Reasoning under uncertainty (probabilistic reasoning)
-Learning
-Agent architectures
-Robotics and perception
-Natural language processing

22
Q

What are examples of successes of AI(3)?

A

-Optical Character recognition(OCR)
-Speech recognition
-Spell checker and grammar checker

23
Q

What’s a more pragmatic def of AI today?

A

AI research is that which computing scientists do not know how to do cost-effectively today.

24
Q

What are the years of creation of AI?

A

1940-1956:

1943: early work in neural netowrks
1950: alan turing describes the turing test
1956: the darmouth workshop

25
What is the darmouth workshop?
-Get-together of the big guys: McCarthy, Minsky, Shannon,etc. -The term AI is first adopted
26
What does the rise of AI(1956-70s) consist of?
-GOFAI-> Good OId Fashioned AI -LISP -PROLOG
27
What is GOFAI(2)?
-Symbolic computation rather than numeric computation -Higher level of abstraction
28
What is LISP(3)?
-Functional language (recursive functions) -McCarthy 1958 -Gave rise to SCHEME, ML,...
29
What is PROLOG(3)?
-Logical language (first-order predicate logic) -Colmeraurer 1972 for NL understanding -Based on Robinson's resolution method for theorem proving
30
What are AI programming languages today?
-General-purpose programming languages like C,C++,Java,... -Current #1 for AI: Python
31
Why are we using general-purpose programming languages today?
Because of the decline in symbolic computations in AI
32
When was the first major of AI winter?
Late 60s-early 70s
33
When did expert systems start and end?
-Start: 1970s-1980s -End : mid 80s-mid 90s
34
What are expert systems?
-Knowledge-intensive, rule-based techniques -Commercial expert systems -Decision-support systems -Humans need to write the rules by hand
35
Why did expert systems end?
-Too tedious to write rules by hand -Too expensive to maintain
36
When did Machine Learning rise?
-1980s-2010 -Rules are now learned automatically
37
Why Machine Learning?
-More powerful CPUs->usable implementation of neural networks -Big data->huge data sets are available
38
When did Deep Learning rise?
-2010-today
39
Why Deep Learning?
-Trained on massive data sets -Use of GPU for computations -Use of generic networks for many applications(image recognition, self driving cars...)
40
What is Eliza?
-Joseph Weizenbaum 1960s -Simulation of a dialogue with a psychotherapist -Great success at the time -Example of a simple production system