Machine Learning

• Model of Learning Agents
  • Distinguish between intelligence and learning
  • Many different learning algorithms and schemes
    • Decision trees
    • Neural networks
    • Inductive logic programming
    • Genetic algorithms
    • Self modifying algorithms

• Forms of learning
  • Unsupervised learning
    • Learn similar situations.
    • Can be used to group sensor readings, and use to choose transformations which work well for the group.
  • Supervised learning
    • Learn input-to-output mappings from preexisting cases.
    • Can be used to learn outcomes of transformations, with the problem and transformation as input, and the result (acquired by the sensors) as the output. Once the mappings are learned they can be used to predict outcomes.
  • Reinforcement learning
    • Learn the quality of an action by evaluation from critic.
    • Can be used to learn which transformations to use.

Exam Style Questions