18 - AI

Question 1

dijkstras algorithm

Answer 1

• method of finding shortest path between 2 points on a graph
• based on cost between nodes
  uses - GPS

Question 2

dijkstras algorithm steps

Answer 2

• give the start index a value of 0
• give each vertex connected to the start a working value - if it already has one replace only if lower
• repeat until end vertex is reached and all vertexes are assigned a final value
• trace the route from the end to the start to find the shortest path

Question 3

A* algorithm

Answer 3

• based on Dijkstra but adds a heuristic value (intelligent guess on how far we have to reach the destination directly)
• finds shortest path from start node to destination node

Question 4

how to calculate heuristic

Answer 4

Manhattan method
- find the across and down distance
pythagorus method
- find the direct distance using pythag

Question 5

applications of shortest path

Answer 5

• GPS
• google maps
• modelling spread of disease
• IP routing (packet switching)

Question 6

AI

Answer 6

a machine with cognitive abilities eg problem solving and learning
split into:
- narrow
- general
- strong

Question 7

narrow AI

Answer 7

when a machine has superior performance to a human in one specific task

Question 8

general AI

Answer 8

when a machine has a similar performance to a human in any intellectual task

Question 9

strong AI

Answer 9

when a machine has superior performance to a human in many tasks

Question 10

examples of AI

Answer 10

• news generation based on live news feed
• smart home devices

Question 11

machine learning

Answer 11

subset of AI
- algorithms are trained and learn from their past mistakes and examples
- is possible for the system to make predictions and even take decisions based on previous scenarios
- offer fast and accurate outcomes due to very powerful processing capability
- have ability to manage and analyse
considerable volumes of complex data (would take humans to long)

Question 12

machine learning eg search engine

Answer 12

• user types criteria into engine which uses search bots to locate websites matching
• user choses one of the websites on page 1 (classed as a success since relevant pages are on 1)
• if user has to go to page 2, 3 or 4 (classed as failure since relevant pages not on 1)

Question 13

unlabelled data

Answer 13

data which is unidentified and needs to be recognised.
Some processing would need to be done before it can be recognised asa specific group

Question 14

types of machine learning

Answer 14

• supervised
• unsupervised
• reinforcement
• semi-supervised (active)

Question 15

supervised learning

Answer 15

makes use of regression analysis and classification analysis - used to predict outcomes based on past data
- needs input + correct outputs to train
- uses labelled data so desired output is known
- once trained - run using labelled data
- results compared with correct output - if errors needs refinement
- once trained run with unlabelled data to predict the outcome

Question 16

supervised learning eg

Answer 16

eg classifying emails as spam, identifying handwriting

Question 17

unsupervised learning

Answer 17

• identify hidden patterns from input data
• not trained using right answer
• by making data more organised patterns become evident
  (uses density estimation and k-mean clustering to do so)
• evaluate the data to find any hidden patterns or structures within the data set

Question 18

unsupervised learning eg

Answer 18

eg product marketing
- a group of individuals with similar purchasing behaviour are regarded as a single unit for promotions

Question 19

reinforcement learning

Answer 19

• learns on reward and punishment - uses trial and error to determine which gives the optimal outcome
• increase the efficiency of the system by making use of optimisation techniques

Question 20

reinforcement learning eg

Answer 20

search engines, online games, robotics

Question 21

semi supervised learning

Answer 21

• makes use of labelled and unlabelled data to train algorithms that can interactively query the source data and produce the desired output
• makes use of as much unlabelled data as possible (cheaper)
• small amount of labelled data is used

Question 22

semi supervised learning eg

Answer 22

classification of web pages
- a web crawler is used to look at large amounts of unlabelled web pages (cheaper than manually annotating them)

Question 23

deep learning

Answer 23

subset of machine learning
structures algorithms in layers (input, hidden, output) to create and ANN that can learn and make intelligent decisions on its own
modelled on human brain

Question 24

reasons for using deep learning

Answer 24

• identify patterns which would be too complex or time consuming for humans
• recognise objects and make them become labelled data which can be used to train new systems
• More precise and accurate - with more hidden layers
• Uses unstructured data
• Outperforms other methods if larger data size

Question 25

artificial neural networks

Answer 25

- based on the human brain - Weights assigned to connections between nodes - Data input and passed into system - Analysed at each subsequent hidden layer where characteristics are extracted - Repeated to achieve optimum outputs - labelled data is used to make sure response is correct if not refined using back propagation

Question 26

reasons for multiple hidden layers

Answer 26

More layers means its weights are more fine-tuned - input nodes can be mapped more accurately to output nodes

Question 27

uses of deep learning

Answer 27

text mining computer assisted translation photograph enhancement turning monochrome to colour chatbots

Question 28

text mining

Answer 28

- text is translated into digital format - then analysed - machine learning used to determine book genre

Question 29

computer assisted translation

Answer 29

- uses terminology database - linguistic databases that grow and ‘learn’ from translations being carried out - uses translation memories - automatically insert known translations for certain words, phrases

Question 30

photograph enhancement

Answer 30

deep learning trained by comparing smartphone and DSLR photos photo is enhanced to DSLR quality by deep learning large number of photographs already taken by a DSLR camera (but not by the smartphone) are then used to test the model

Question 31

turning monochrome photos into colour

Answer 31

deep learning can be used to give a very accurate coloured image trained by searching websites for data which allows it to recognise features then map a colour to a photograph

Question 32

chatbots

Answer 32

interact through instant messaging, artificially replacing patterns of human interaction using ML typed messages or voice recordings make use of predefined scripts and ML when a question is asked, a chatbot responds using the information known at the time

Question 33

ML vs DL

Answer 33

- ML enables machine to make decisions based on past data - DL uses an ANN - ML only needs a little data to train - DL needs lots - ML identifies most features in data in advance - DL learns features of data from the data itself - ML uses modular approach - DL solves as one entity - ML takes long to test - DL testing is short - ML has clear rules explaining why each models stage was made - DL makes decisions based in its own reasoning - hard to understand (black box)

Question 34

future

Answer 34

AI - detection of crimes before they happen, development of humanoid AI to carry out human tasks ML - increased efficiency of health diagnostics, better marketing DL - increased personalisation in areas eg individual cancer care, hyper intelligent personal assistants

Question 35

back propagation

Answer 35

- initially random weightings - initial output compared with expected - weights adjusted to minimise difference - calculus used to find error gradient in outputs - results fed back into ANN and weightings adjusted - once errors in output eliminated the ANN is functioning correctly - if errors still large repeated

Question 36

types of back propagation

Answer 36

static - maps static inputs to static input - mapping is instantaneous - training is easier recurrent - activation is fed forward until a fixed value is achieved - not instantaneous mapping - training is harder

Question 37

regression

Answer 37

- way of analysing data before it is input into a system or model - used to make predictions from given data by learning some relationship between the input and the output - helps in the understanding of how the value of a dependent variable changes when the values of independent variables are also changed - used in prediction eg weather forecasting - in ML used to predict the outcome of an event based on any relationship between variables