the learning problems

• When Can Machines Learn? (illustrative + technical)
• Why Can Machines Learn? (theoretical + illustrative)
• How Can Machines Learn? (technical + practical)
• How Can Machines Learn Better? (practical + theoretical)

Learning: acquiring skill with experience accumulated from observations

Machine learning: acquiring skill with experience accumulated/computed from data

data ——-> ML ———> sklill

Skill: improve some performance measure (e.g. prediction accuracy)

data ——-> ML ———> improved performance measure

ML: an alternative route to build complicated systems

Give a computer a fish, you feed it for a day; teach it how to fish, you feed it for a lifetime

Improving some performance measure with experience computed from data

• exists some underlying pattern to be learned
• but no programmable (easy) definition
• somehow there is data about the pattern

• inputs: $x in chi$

• outputs:$yin gamma$

• unknown pattern to be learned <=> target function

$$f: chi rightarrow gamma$$

• data <=> training examples

  $$D = {(x_1,y_1),(x_2,y_2),......(x_N,y_N)}$$

• hypothesis <=> skill with hopefully good performance

$$g: chi rightarrow gamma$$

Machine Learning: use data to compute hypothesis g that approximates target f

• Machine Learning

use data to compute hypothesis g that approximates target f. ML can realize AI, among other routes($g approx f$ is something that shows intelligent behavior)

• Data Mining

use (huge) data to find property that is interesting.

• Artifical Intelligence

compute something that shows intelligent behavior.

• Statics

use data to make inference about an unknown process, statistics is a useful tool for ML.