On the identifiability of mixtures-of-experts

Neural Networks

Volumn 12, Issue 9, 1999, Pages 1253-1258

  Jiang, W ^a   Tanner, M A ^a  

^a NORTHWESTERN UNIVERSITY   (United States)

Author keywords

Generalized linear models; Indentifiability; Invariant transformations; Mixtures of experts

Indexed keywords

COMPUTER ARCHITECTURE; EXPERT SYSTEMS; MATHEMATICAL MODELS; MATHEMATICAL TRANSFORMATIONS; PROBABILITY DENSITY FUNCTION;

GATING FUNCTIONS; INVARIANT TRANSFORMATIONS; MIXTURE OF EXPERTS (ME);

NEURAL NETWORKS;

ALGORITHM; ANALYTIC METHOD; ARTICLE; CHANNEL GATING; COVARIANCE; NERVE CELL NETWORK; PRIORITY JOURNAL; PROBABILITY; STATISTICAL ANALYSIS; THEORY;

EID: 0032863989     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0893-6080(99)00066-0     Document Type: Article

References (15)

1. Cacciatore T.W., Nowlan S.J. Mixtures of controllers for jump linear and non-linear plants. Tesauro G., Touretzky D.S., Leen T.K. Advances in neural information processing systems. 6:1994;Kaufmann, San Mateo, CA.
2. Ghahramani, Z. & Hinton, G.E. (1996). The EM algorithm for mixtures of factor analyzers. Technical Report CRG-TR-96-1, Department of Computer Science, University of Toronto, Toronto, Ontario.
3. Jaakkola T.S., Jordan M.I. Improving the mean field approximation via the use of mixture distributions. Jordan M.I. Learning in graphical models. 1998;Kluwer Academic, Dordrecht.
4. Jacobs R.A., Jordan M.I., Nowlan S.J., Hinton G.E. Adaptive mixtures of local experts. Neural Computation. 3:1991;79-87.
5. Jiang W., Tanner M.A. On the approximation rate of hierarchical mixtures-of-experts for generalized linear models. Neural Computation. 11:1999;1183-1198. in press.
6. Jordan M.I., Jacobs R.A. Hierarchical mixtures of experts and the EM algorithm. Neural Computing. 6:1994;181-214.
7. Jordan M.I., Xu L. Convergence results for the EM approach to mixtures-of-experts architectures. Neural Networks. 8:1995;1409-1431.
8. Meila, M. & Jordan, M.I. (1995). Learning fine motion by Markov mixtures of experts. A.I. Memo No. 1567, Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA.
9. Redner R.A., Walker H.F. Mixture densities, maximum likelihood and the EM algorithm. SIAM Review. 26:1984;195-202.
10. Sussmann H.J. Uniqueness of the weights for minimal feedforward nets with a given input-output map. Neural Networks. 5:1992;589-593.
11. Teicher H. On the mixture of distributions. Annals of Mathematical Statistics. 31:1960;55-73.
12. Teicher H. Identifiability of finite mixtures. Annals of Mathematical Statistics. 34:1963;1265-1269.
13. Tipping, M.E. & Bishop, C.M. (1997). Mixtures of probabilistic principal component analysers. Technical Report NCRG-97-003, Department of Computer Science and Applied Mathematics, Aston University, Birmingham, UK.
14. Titterington D.M., Smith A.F.M., Makov U.E. Statistical analysis of finite mixture distributions. 1985;Wiley, New York.
15. Yakowitz S.J., Spragins J.D. On the identifiability of finite mixtures. Annals of Mathematics and Statistics. 39:1968;209-214.