AI

Question 1

Explain the difference between weak AI and strong AI. What are their assumptions and what does that
mean for AI?

Answer 1

Weak:

• non-sentient
• focused on narrow task
• based on rule-based manipulation (eg. if… then…)
• not ‘truly intelligent’
• Searle: chinese room argument= doesn’t reflect true intelligence

strong:
- can think
- requires connectionist architecture
- assumes human mind to be an info processing system
= thinking= form of computing

Question 2

Explain the difference between symbolic AI and connectionist AI.

Answer 2

symb:

• rule-based (symbol manipulation)
• no pattern recognition
• cannot classify objects or deal w noisy input

c:

• based on networks similar to neurobiology (parrallel processing)
• can solve complex non-linear problems
• can generalise novel input (learn)

Question 3

What was Turing’s imitation game about and how does this relate to intelligent systems?

Answer 3

game:
- if machine indistinguishable from human,
= must be intelligent

• doesn’t question underlying mechanism
• is it actually intelligent?

Question 4

How does Searle’s Chinese room argument relate to Turing’s imitation game? What conclusions would
Searle draw out of a computer passing the imitation game?

Answer 4

• even when programmed to answer all questions correctly, it doesn’t mean intelligence
• doesn’t understand essence of chinese
• simply programmed to answer

Question 5

Explain the criticism on symbolic AI. Give arguments against and for.

Answer 5

for:
- MYCIN was v successful (diagnosing blood infections)

against:

• highly inflexible (relies on programmed symbols
• cant deal w noise
• can’t reach human-like intelligence

Question 6

What are the similarities between connectionist AI architectures and the human brain?

Answer 6

• based on the structure of a human brain
• parallel processing
• can generalise (learn)

Question 7

What does it mean for human memory to be content-addressable?

Answer 7

• means that memory can be retrieved by using content as cue

- possible due to memory not stored in neurons but in the connections b/n them

Question 8

What is an expert system?

Answer 8

representation of an expert’s knowledge of a subject

Question 9

what are expert system’s components and their functions?

Answer 9

knowledge base:

• knowledge about the world
• how concepts relate to each other

inference engine:
- manipulate the symbols
eg . predicate logic

Question 10

Explain how a conclusion is deduced in an expert system using forward and backward chaining. What are
the algorithms of both chaining directions?

Answer 10

forward:
- sequential until solution found
- if then rules applied
- facts are matched
= deduce conclusion

backward:
- have a hypothesis
- use if then rule backwards
- check if antecedents be true until hypo accepted/ rejected
- if all antecedents accepted= conclusion
(skips unneccesary qustions)

Question 11

When should you use forward chaining, and when backward chaining?

Answer 11

• f when want to know everything you can from a set of facts

- b when not all facts are known

Question 12

Sudoku:
Explain the backtracking
algorithm and give an algorithmic implementation of backtracking in solving a Sudoku.

Answer 12

• iteratively generating possible solutions
• when realise that it doesn’t lead to a complete solution
• goes back to previous choice and creates a new solution

Question 13

what is the difference between depth-frst search and breadth-frst search?

Answer 13

DFS:

• goes to 1 child and expand on all its children before expanding on the next child and all its children
• alternatives are ignored
• backtracks when deadend met

BFS:
- expands on everything on first layer before moving on to the next layer

Question 14

Which type (BFS/ DFS) should be used
under what circumstances? Explain.

Answer 14

BFS

• used when v deep trees
• not when all paths would reach goal about the same time

DFS

• used when trees not that deep
• goal expected to be found after a reasonable amount of steps

Question 15

How does a heuristically informed algorithm differ from its naive counterpart?

Answer 15

has more info than naive counterparts

- allows for better decisions

Question 16

We can heuristically inform depth-frst and breadth-frst search using, for example, a distance-to-target
metric. Name the two algorithms that result from this, and explain how they work.

Answer 16

GREEDY ALGORITHMS
(choose locally best choice at each stage)

hill-climbing

• moves similar to DFS
• uses shortest distance to target as heuristic

beam search

• modified BFS
• moves thru the best nodes

Question 17

In optimal search, the branch-and-bound algorithm works by discarding some branches. Explain which
branches are discarded by the algorithm and why.

Answer 17

(uniform-cost search)

• it ignores path w distances that are equal or greater than the distance for that solution
• benefits from the having the estimated distance left
• discards redundant paths for more efficiency

Question 18

The A* algorithm combines three techniques that were discussed in the lectures. Name these 3
techniques, and how they contribute to efficient path finding.

Answer 18

• branch-and-bound
• distance estimates
• redundant path removal
• efficient thru evaluating the cost to the node and the cost from the node to the goal

Question 19

Give a definition and an example of combinatorial explosion.

Answer 19

• rapid growth of the complexity and possible solutions to a problem
• eg. trying to solve sudoku by using naive brute force

Question 20

What does it mean when a game (e.g. checkers, chess) is solved?

Answer 20

when optimal steps for each player can be calculated

Question 21

Explain why robots need sensors and effectors, and include their defnitions.

Answer 21

sensors:
- allows to perceive environment

effectors:
- so it can move

Question 22

What are degrees of freedom in robotics? Give an example.

Answer 22

• independent parameters that define the system’s configuration
• eg. drone has 6 df
  3 for location and 3 for angular orientation

Question 23

How does the behavior of two Braitenberg Vehicles differ between straight vs. crossed excitatory
connections? Describe their behavior exhaustively

Answer 23

straight: fear
- turns away from signal and slows down as it goes further away

crossed: aggression
- turns toward signal
- faster as closer to signal

L3

Question 24

What happens to these two vehicles if we make the connections inhibitory?

Answer 24

LOVE

straight: love
- race toward signal
- stops in front of it

crossed: unfaithful lover
- orient itself away from signal
- speed up as further from signal

Question 25

What happens when we implement a threshold function?

Answer 25

• will appear to make its own decision

= have own values

Question 26

Explain the concept of evolutionary robotics using pseudocode.

Answer 26

(genetic algorithm)

• choose population
• evaluate each individuals’ fitness
• only keep best performing robots
• replenish population w well-performing robots
• terminate when fitness reached a plateau

Question 27

Name two robot learning techniques

Answer 27

motor babbling:

reinforcement learning:

Question 28

motor babbling

Answer 28

robot learning technique

• random movements initially (M)
• until movement changes body configuration and environment (K)
• co-activation b/n M&K= bidirectional associations
• could also learn by human guiding movements (imitation learning)
• build model of required movement

Question 29

reinforcement learning

Answer 29

robot learning technique

• send reinforcement signal to the control system
• signal usually binary (altho other values possible)
• tells machine whether it passed/ failed