Lec 1-2

Question 1

Machines with minds, in the full and literal sense

Answer 1

Thinking - human/antropomorphic

Question 2

Study of mental faculties

Answer 2

Thinking - rationality

Question 3

Creating machines that perform functions that require intelligence

Answer 3

Acting - human/antromorphic

Question 4

Explain and emulate intelligent behavior in terms of computational processes

Answer 4

Acting - rationality

Question 5

Early examples AI

Answer 5

• Greek mythology, artificial beings
• Aristotle (BC) and Leibniz (1700) reduce logical thinking to formal calculus
• Babbage (1800) analytical engine
• Lovelace (1800) programs for engine
• Fiction
• Turing Test
• Shannon Computer Chess

Question 6

Early computer science

Answer 6

• 1955 Logic theory Newell and Simon
• Machine learning computer checkers mid 1950’s

Here is where it took off with the advent of modern computers

Question 7

Why are games useful for AI algorithms

Answer 7

• Clearly structured
• Clear goals/tasks
• Limited enough to be tractable
• Complex enough to be interesting

Question 8

What is a microworld?

Answer 8

• Bounded domain
• Unambiguous and simple/simplified structure
• Clear and measurable goals
• As opposed to games; not necessarily competitive

Question 9

Problems with game tree

Answer 9

It grows exponentially, with m moves/turn and d turns/game O(m^d) terminal states. Becomes computationally intractable

Question 10

What is the idea behind a Heuristic Evaluation Function?

Answer 10

Somehow estimate “value” of state without expanding whole tree. It assigns a numerical score to any game state.

Might be handcrafted or learned with NNs

Question 11

What is the basic idea of MiniMax algorithm?

Answer 11

• Optimise short-term tactical play using game tree expansion
• Score leaves with evaluation function at non-terminal depth

Question 12

What are different names for Connectionist AI

Answer 12

• Connectionism
• Parallel Distributed Processing (PDP)
• Artificial neural networks
• Deep learning

Question 13

What is the basic idea of connectionist AI:

Answer 13

Inspired by the human brain (not simulation).

Question 14

What is the McCulloch & Pitts artificial neuron? (1943)

Answer 14

Binary neuron output. Different types of connections (excitatory, weights are positive vs inhibitory, weights are negative)

Question 15

How does BTAN (Binary Threshold Artificial Neuron) work?

Answer 15

It receives n inputs gives 1 output O
All inputs are binary and have either a negative or positive weight
Activation is weighted sum of inputs
Threshold activation function with threshold

Question 16

What are synonyms for Symbolic AI?

Answer 16

GOFAI (Good old Fashioned AI)

Question 17

What are the features of Symbolic AI?

Answer 17

Explicit knowledge representation
- roughly human readable, knowledge is represented by symbols

It can encode relations between symbols with expressions/symbol structures
Such expressions are also knowledge.
Reasoning is resolving expressions into conclusions using rules

This reduces reasoning to a search problem

Question 18

Separating knowledge and processing

Answer 18

Symbolic AI (in contrast to Connectionist)

Question 19

What were initial uses of Automatic Computers

Answer 19

Numerical and for military purposes. (Code-breaking, ballistic trajectories, computations for hydrogen bomb)

Chess (Shannon), and Logic Reasoning were cautiously explored, non-numerical problems

Question 20

What was the Dartmouth Workshop and the goal of it?

Answer 20

2 month, 10 man study of AI. Proceeding the basis of the conjecture that every aspect of learning or any other feature of intelligence can be described such that a machine can be made to simulate it.

Question 21

What was the initial idea the researchers had with the Dartmouth Proposal?

Answer 21

An attempt to find how machines are able to use language, form abstractions and concepts, solve kinds of problems now reserved for humans and improve. They thought to make significant advance in one or more of these problems.