←
^
→
Combining Inductive and Analytical Learning
EBNN Summary
EBNN has been shown to generalize more accurately than backpropagation, especially when training data is scarce.
It has been used to learn to control a simulated mobile robot.
EBNN, like Prolog-EBG, constructs explanations, but they are based on a domain theory consisting of neural networks rather than Horn clauses.
EBNN accommodates imperfect domain theories.
EBNN learns a fixed size network, so it might be unable to represent complex functions.
José M. Vidal
.
26 of 32