Nemenman, 2005

From Ilya Nemenman: Theoretical Biophysics @ Emory
Revision as of 12:28, 4 July 2018 by Ilya (talk | contribs) (1 revision imported)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to: navigation, search

Back to the full Publications list.

I Nemenman. Fluctuation-dissipation theorem and models of learning. Neural Comp., 17(9):2006-2033, 2005. PDF, arXiv.

Advances in statistical learning theory leave us with many possible designs of learning machines. But which of them are implemented by brains, metabolic and genetic networks, and other biological information processors? We analyze how various abstract Bayesian learners would perform on different data, including natural ensembles, and discuss possible experiments that can determine which learning-theoretic computation is performed by a particular organism.