Path: utzoo!censor!geac!torsqnt!lethe!yunexus!ists!helios.physics.utoronto.ca!news-server.csri.toronto.edu!cs.utexas.edu!bcm!dimacs.rutgers.edu!aramis.rutgers.edu!paul.rutgers.edu!kadirkam From: kadirkam@paul.rutgers.edu (Janardhanan Kadirkamanathan) Newsgroups: comp.ai.neural-nets Subject: Tech Report available Message-ID: Date: 21 Nov 90 19:47:14 GMT Organization: Dept. of Computer Science, Rutgers The State University. Lines: 48 Message forwarded from visakan@eng.cam.ac.uk follows: --------------------------------------------------------- The following technical report is available: f-Projections: A nonlinear recursive estimation algorithm for neural networks V.Kadirkamanathan, M.Niranjan & F.Fallside Technical Report CUED/F-INFENG/TR.53 Cambridge University Engineering Department Trumpington Street, Cambridge CB2 1PZ, England Abstract By addressing the problem of sequential learning in neural networks, we develop a new principle, f-projection, as a general method of choosing a posterior estimate of a function, from the new information received and the prior estimate. The principle is based on function approximation and the posterior so obtained is optimal in the least L-2 norm sense. The principle strikes a parallel with minimum cross entropy, which provides a method of choosing a posterior probability density estimate. Some fundamental properties of the principle of f-projection are given with formal proofs. Based on the principle of f-projection, a recursive (sequential) estimation method called the method of successive f-projections, is proposed. Some convergence related properties for this method are given with formal proofs. The method is extended for parameter estimation and to a sequential training algorithm for neural networks. The problem of combining two separately trained neural networks is also discussed. Please send requests to: Visakan Kadirkamanathan Speech Laboratory Cambridge Unviersity Engineering Department Trumpington Street Cambridge CB2 1PZ England email: visakan@eng.cam.ac.uk -----------------------------------------------------------------------