Lecture 1 & 2 - What is AI and Adaptive Systems

Question 1

What is AI?

Answer 1

AI stands for Artificial Intelligence, referring to the ability of computer systems to perform tasks that typically require human intelligence, such as learning, reasoning, and decision-making.

Question 2

What is the Four Quadrant of AI?

Answer 2

Made up of:
Thinking (Top)
Rationality (Right)
Acting (Bottom)
Humanly (Left)

Question 3

What are Adaptive Systems?

Answer 3

An adaptive system are interdependent entities, real or abstract, forming an integrated whole that together are able to respond to environmental changes or changes in the interacting parts. - Related to biology

Question 4

What is a Complex Adaptive System?

Answer 4

How individuals create changing patterns and how those patterns affect themselves and things around them

Question 5

Why is adaption important?

Answer 5

• Real-world environments are dynamic, messy, and uncertain.
• Adaptation = resilience and flexibility.

Question 6

What are the mechanisms of adaption?

Answer 6

• Short-term: learning (individual level), physical adaptation (to environment, etc).
• Long-term: evolution (population level), social/emergent behaviour.

Question 7

What is Computer Intelligence?

Answer 7

“Computational Intelligence (CI) is the theory, design, application and development of biologically and linguistically motivated computational paradigms. Main pillars of CI are Neural Networks, Fuzzy Systems and Evolutionary Computation
Such as
* Nature-inspired problem-solving.
* Sub-symbolic methods like:
○ Neural networks
○ Evolutionary algorithms
○ Swarm intelligence

Question 8

What is Symoblic in reference to AI?

Answer 8

• Symbolic
  ○ ‣ Declarative
  ○ ‣ Rules (rule based)
  ○ ‣ Designed or learnt
  ○ ‣ More human interpretable

Question 9

What is Non-Symbolic in reference to AI?

Answer 9

• Sub-Symbolic
  ○ ‣ Networks/connectionist
  ○ ‣ Weights/parameters
  ○ ‣ Learnt or evolved
  ○ ‣ Less human interpretable

Question 10

What is Soft Computing?

Answer 10

Soft = tolerant of imprecision, uncertainty. -> focuses on approximate models and solutions to complex real-world problems by tolerating imprecision, uncertainty, and partial truth
○ Suitable for “messy” real-world problems.

Question 11

What is Hard Computing?

Answer 11

Hard (traditional) = emphasizes precision, certainty, and rigor, relying on precisely stated analytical models and sequential, deterministic algorithms to solve problems