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 edit
References edit
- ^ a b O'Reilly, R.C. Biologically Plausible Error-driven Learning using Local Activation Differences: The Generalized Recirculation Algorithm. Neural Computation, 8, 895–938. Abstract PDF
- ^ GeneRec description in Computational explorations in cognitive neuroscience: understanding the mind by Randall C. O'Reilly, Yuko Munakata
- ^ Leabra overview in Emergent
 | This neuroscience article is a stub. You can help Wikipedia by expanding it. |