GeneRec

GeneRec is a generalization of the recirculation algorithm, and approximates Almeida–Pineda recurrent backpropagation. It is used as part of the Leabra algorithm for error-driven learning.

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

See also

References

  1. 1 2 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. ↑ GeneRec description in Computational explorations in cognitive neuroscience: understanding the mind by Randall C. O'Reilly, Yuko Munakata
  3. ↑ "Leabra overview in Emergent". Archived from the original on 2009-04-16. Retrieved 2010-04-26.