ClimBS: Searching the Bias Space

  • Foster Provost

The literature on systems that address the selection of inductive bias explicitly is reviewed and a model of inductive bias selection as state space search, which is instantiated in a test bed system with biases as states and bias transformation operators used to move from state to state, is introduced.  The test bed allows a system developer to address different dimensions in the bias space and different policies for bias selection by adding the appropriate operators.  The ClimBS system has been developed in this test bed as one policy for bias selection modeled after manual bias selection strategies; the system’s performance is measured on several domains from the UCI repository and on a synthetic domain.  A summary of experiments designed to analyze empirically the system’s performance is provided.