Machine Learning as Bayesian Inference

Machine Learning as Bayesian Inference

• The learning problem:
  • Given: training set x of instances from some concept c
  • Goal: learn which concept c from family X produced the training set
  • There may or may not be “noise” in the training data
• Bayesian inference applied to machine learning
  • Prior distribution P(c) over X
  • Likelihood function P(x|c) for data given concept (may be deterministic)
  • Result of learning: posterior distribution P(c|x) for concept given data

Previous slide

Next slide

Back to the first slide

View Graphic Version