Learning as abstraction
Process of automatically constructing abstractions of the real world from a set of obesrvations and past experiences.
Why should computers learn?
humans might not have experience (navigating on Mars)
humans might be unable to explain their expertise (speech/image recoginition)
solution changes in time
Learning by feedback
Supervised learning
learning from input-output pairs
reinforcement learning
learning from reward of sequence of actions
unsupervised learning
Given: Input-Output-Values (=training data) of Function f
Wanted: Function h that approximates f
h is called hypothesis
accuracy of h is measured using test data
Features
prediciton of future
knowledge extraction (encoded as h)
compression (h < data set)
Supervised learning:
Classification
Output of function is finite set (e.g. red, blue or green) -> input is classified
Example:
Classification - Underfitting
low performance on training data
low performance on testing data
reason: model is too simple and lacks the capacity to capture the complexity of the data (e.g. linear regression for non linear data)
Classification - Overfitting
high performance on training data
reason: model is too complex and captures noise and random variations in the training data (e.g. decision tree is too deep and each leaf has only a few samples)
Regression
Output of function is a number
Reinforcement Learning
AI generatea a sequence of output in order to reach a goal.
For example:
Elevator scheduling
Chess
Robot control
Unsupervised Learning
no ouput data available
try to find patterns in input
Last changed2 years ago
