MAI - topics 5-9

Question 1

Problem (T5)

Answer 1

Situation, question, or thing that causes difficulty, stress, or doubt.

Question 2

Problem Solving Process (T5)

Answer 2

Understand the problem - identify and define
Plan – analyse, form a strategy
Do – resources, organise information
Check – moniter progress, evalutate results

Does not need to be in order

Question 3

Knowledge Representation (T5)

Answer 3

Representation of information from real world for a computer to understand and solve

Question 4

DIKW Model (T5)

Answer 4

Data Information Knowledge Wisdom (pyramid)

Question 5

Data (T5)

Answer 5

Representation of facts, observations and occurrences – raw without processing

Question 6

Information (T5)

Answer 6

Data converted into meaningful form

Question 7

Knowledge (T5)

Answer 7

Facts, skills and understanding gained, through experience, which enhances ability to evaluate context, make decisions and take actions

Question 8

Wisdom (T5)

Answer 8

Ability to act critically or practically in a situation – based on ethical judgement based on an individual’s belief system – application of knowledge centred around a certain criteria

Question 9

Knowledge vs Wisdom (T5)

Answer 9

Knowledge - collection of information through learning, skills and studies, organised information

Wisdom - ability to judge and apply education to practical life

Question 10

Machine Reasoning (T5)

Answer 10

Process of taking information that is known along with background information to make inferences regarding unknown information

Question 11

Knowledge Processing System (T5)

Answer 11

Allows a strategy to make a decision in acquiring knowledge

Machines struggle to interpret all human information – must represent

Question 12

Declarative Knowledge (T5)

Answer 12

Concepts, Facts

Question 13

Structural Knowledge (T5)

Answer 13

Problem solving, relationship between concepts and objects

Question 14

Procedural Knowledge (T5)

Answer 14

Knowing how to do something (rules)

Question 15

Meta Knowledge (T5)

Answer 15

Knowledge about other types of knowledge (planning, learning)

Question 16

Heuristic Knowledge (T5)

Answer 16

Expert knowledge in a field – solves problems based on experience of previous problems

Question 17

KR Components (T5)

Answer 17

Perception – retrieves data
Learning – learns from captured data
Knowledge representation and reasoning –
humanlike intelligence
Planning and execution – depend on analysis from KRR

Question 18

Intelligent Agents (T5)

Answer 18

Anything that can be taken as percieving an environment

Question 19

Structure of an Intelligent Agent (T5)

Answer 19

Sensing – perceiving features of environment
Thinking – decide what action to take
Acting – doing things

Question 20

Machine Learning vs Reasoning (T5)

Answer 20

ML - mathematics, predictions, analytical, training, works on data

Reason - KR, problem solving, expert, works on knowledge

Question 21

Optimisation problems (T6)

Answer 21

Huge proportion of problems we ask computers to solve

Best solution from a number of alternatives

Heuristics

Question 22

Combinatorial optimisation problems (T6)

Answer 22

Find the best combination of discrete values from some given set

Question 23

Combinational Explosion (T6)

Answer 23

Occurs in numeric problems when the complexity rapidly increases, caused by the increasing the number of possible combinations of inputs

Curse of dimensionality

Question 24

Curse of Dimensionality (T6)

Answer 24

Explosive nature of increasing data dimensions and its resulting exponential increase in computational efforts required for its processing

Observed in machine learning

Increase in dimensions add more information – improve quality of data but practically increases noise as well

Question 25

Symbolic AI (T6)

Answer 25

• Must provide all the characteristics in advance
• Able to replicate high level human capabilities
  using recent advances on formal systems and computational capacity
• Decision tree

Question 26

Connectionist AI (T6)

Answer 26

Tries to produce intelligent behavior replicating neural structures: small computational units playing the role of “neurons”

Question 27

Machine Learning (T6)

Answer 27

Field of AI that applies statistical methods to enable computer systems to learn from the data towards an end goal

Uses various types of automated algorithms that learn to model functions and predict future actions from data

Question 28

Deep Learning (T6)

Answer 28

Neural networks with several hidden layers
- training (calibration) and validation (assess)

Uses neural networks that pass data through many processing layers to interpret data features and relationships - forecasting

Question 29

ML vs DL (T6)

Answer 29

ML - thousands of data points, neumerical value, predict future actions, directed by data analyists

DL - millions of data points, numerical to free-form elements, interpretation, largely sefl directed

Question 30

DL Feedforward Networks (T6)

Answer 30

Multi-layered networks, where inputs are weighted and some function transforms the weighted total giving the output, which is the input of the next layer
- use errors to learn

Question 32

Deep Learning Applications (T6)

Answer 32

• Use of neural network for programming
• Classical dynamic programming – based on optimisation
• Reinforcement learning – constructing networks capable of optimal behaviour on a given artificial environment

Question 33

Cognitive Computing (T7)

Answer 33

Try to mimic a human brain by analysing text/speech/sound/images and objects to give a desired outcome (AI-based language translation software)

Question 34

Speech Recognition (T7)

Answer 34

Cognitive service that aims to replicate a human action - processes sproken word and processes it into readable text

Question 35

Speech Recognition Applications (T7)

Answer 35

Transcription, voice-based search engines, produces data for analysis

Question 36

Computer (T8)

Answer 36

Device that can be instructed to carry out sequences of arithmetic or logical operations automatically or computer programming

Question 37

Robot (T8)

Answer 37

Machine which may or may not require intelligence, specific tasks, physical form

Question 38

AI (T8)

Answer 38

Ability for a computer or robot to perform tasks associated with intelligent beings

Question 39

Robot Types (T8)

Answer 39

Autonomous/semi-autonomous

Question 40

Robotics Applications (T8)

Answer 40

Assembly, customer service, packaging, open source robotics (AI)