Inductive bias

The inductive bias of a learning algorithm is the set of assumptions that the learner uses to predict outputs given inputs that it has not encountered

—(Mitchell, 1980), The need for biases in learning generalizations

In Bayesian framework, inductive bias is encoded in the prior distribution.

See Also

• Prior distribution
• Bias (statistics)

References

Overcoming Bias Articles

• "Inductive Bias" by Eliezer Yudkowsky