intro to machine learning

what is machine learning

a computer program is said to learn

• from experience E

• with respect to some class of tasks T

• and performance measure P

if its performance at tasks in T, as measured by P, improves with experience E.

what is the difference between AI, machine learning and deep learning

AI: any technique which enables computers to mimic human behavior

Machine Learning: AI techniques that give computers the ability to learn without being explicitly programmed to do so

Deep Learning: A subset of Machine Learning which make the computation of multi-layer neural networks feasible

what are the types of machine learning

1. supervised learning

• input:

  • training samples

  • desired output (teacher/supervision)

• output:

  • a rule that maps input to output

2. unsupervised learning

• input: samples

• output: underlying patterns in data

3. reinforcement learning

• input: sequence of states, actions, and delayed rewards

• output: action strategy: a rule that maps the environment to action

what are the 2 types of supervised learning

• regression

• classification

what is the difference between unsupervised learning and supervised learning

no label/supervision is given

what is a type of unsupervised learning

clustering

what is reinforcement learning

• given a sequence of states S and actions A with (delayed) rewards R

• output a policy to guide us what action to take in state S

what are 2 ways of classification

1. feature extraction

• extract attributes of samples

2. sample classification

• decide label for a sample

what are the 2 types of reasonings

1. inductive inference

• to reach probable conclusions

• not all needed information is available, causing uncertainty

  • probability and statistics

2. deductive inference

• to reach logical conclusions deterministically

• all information that can lead to the correct conclusion is available

  • rule-based reasoning