GeneRec explained

GeneRec is a generalization of the recirculation algorithm, and approximates Almeida-Pineda recurrent backpropagation.^{[1] [2]} It is used as part of the Leabra algorithm for error-driven learning.^[3]

The symmetric, midpoint version of GeneRec is equivalent to the contrastive Hebbian learning algorithm (CHL).^[1]

See also

• Leabra
• O'Reilly (1996; Neural Computation)

Notes and References

1. O'Reilly, R.C. Biologically Plausible Error-driven Learning using Local Activation Differences: The Generalized Recirculation Algorithm. Neural Computation, 8, 895–938. Abstract PDF
2. https://books.google.com/books?id=BLf34BFTaIUC&dq=recirculation+algorithm&pg=RA1-PA162 GeneRec description in Computational explorations in cognitive neuroscience: understanding the mind by Randall C. O'Reilly, Yuko Munakata
3. http://grey.colorado.edu/emergent/index.php/Leabra Leabra overview in Emergent