01 Introduction to Machine Learning*

Question 1

what is the power hypothesis

Answer 1

if program perform complex task well, it must know a great deal about the domain it operates in

Question 2

what is the breadth hypothesis

Answer 2

to behave intelligently in unexpected situations, an agent must be capable of falling back on increasing knowledge

Question 3

what is machine learning

Answer 3

ever-growing set of algorithms

Question 4

supervised learning- regression

Answer 4

learning from a continuous function from a set of examples
eg. predicting stock prices

Question 5

supervised learning- classification

Answer 5

learning rules that can separate objects of different type from one another
eg. disease diagnosis, spam email detection

Question 6

unsupervised learning- clustering

Answer 6

finding groups of similar object
eg. people with similar preferences, genes with similar functions

Question 7

unsupervised learning- projection

Answer 7

reducing number of dimensions
eg. visualise complex data

Question 8

reinforcement learning

Answer 8

control learning: take action to maximise rewards
eg. gaming, robot navigation