GeneRec is a generalization of the recirculation algorithm, and approximates Almeida-Pineda recurrent backpropagation.
[O'Reilly, R.C. Biologically Plausible Error-driven Learning using Local Activation Differences: The Generalized Recirculation Algorithm. Neural Computation, 8, 895–938]
AbstractPDF
/ref> It is used as part of the Leabra algorithm for error-driven learning.Leabra overview in Emergent
/ref>
The symmetric, midpoint version of GeneRec is equivalent to the contrastive Hebbian learning algorithm (CHL).
See also
* Leabra
O'Reilly (1996; Neural Computation)
References
Neuroscience
Machine learning algorithms
{{machine-learning-stub