论文信息 - A learning law for density estimation

A learning law for density estimation

Probability density functions are estimated by an exponential family of densities based on multilayer feedforward networks. The role of the multilayer feedforward networks, in the proposed estimator, is to approximate the logarithm of the probability density functions. The method of maximum likelihood is used, as the main contribution, to derive an unsupervised backpropagation learning law to estimate the probability density functions. Computer simulation results demonstrating the use of the derived learning law are presented.

Yeshaiahu Fainman | Dharmendra S. Modha

[1] Geoffrey E. Hinton,et al. A Learning Algorithm for Boltzmann Machines , 1985, Cogn. Sci..

[2] Halbert White,et al. Approximating and learning unknown mappings using multilayer feedforward networks with bounded weights , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[3] Andrew R. Barron,et al. Minimum complexity density estimation , 1991, IEEE Trans. Inf. Theory.

[4] A. Barron,et al. APPROXIMATION OF DENSITY FUNCTIONS BY SEQUENCES OF EXPONENTIAL FAMILIES , 1991 .

[5] Geoffrey E. Hinton,et al. Learning internal representations by error propagation , 1986 .

[6] L. Jones. A Simple Lemma on Greedy Approximation in Hilbert Space and Convergence Rates for Projection Pursuit Regression and Neural Network Training , 1992 .

[7] J. Neyman. »Smooth test» for goodness of fit , 1937 .

[8] C. J. Stone,et al. Large-Sample Inference for Log-Spline Models , 1990 .