Introduction

Weak Artificial Intelligence

• A system designed to carry out one particular job
• Video games such as the playing chess, personal assistants such as Amazon's Alexa and Apple's Siri

Strong artificial intelligence

• Systems that carry on the tasks considered to be human-like
• More complex and complicated systems
• Solve a problem without having a person intervene, like self-driving cars or in hospital operating

Machine learning involves data collection, model building, and optimization.

Training data - a set of instances (examples) with

• inputs (features, attributes)

  • quantitative (continuous)
  • qualitative (discrete)

• output (label)

  • quantitative (regression)
  • qualitative (classification)

Model - a way to describe the relation between input features and output label

Optimization - choose the best model parameters subject to some criterion

Categorization of ML algorithms

• Based on tasks

  • Regression, classification, clustering, ranking, etc

• Based on methodologies

  • Discriminative vs generative

• Based on availability of labels

  • yes: supervised
  • no: unsupervised
  • partially: semi-supervised

• Based on depth

  • Deep vs shallow

History of machine learning