Semi-unsupervised Weighted Maximum-Likelihood Estimation of Joint Densities for the Co-training of Adaptive Activation Functions
The paper presents an explicit maximum-likelihood algorithm for the estimation of the probabilistic-weighting density functions that are associated with individual adaptive activation functions in neural networks. A partially unsupervised technique is devised which takes into account the joint distribution of input features and target outputs. Combined with the training algorithm introduced in the companion paper , the solution proposed herein realizes a well-defined, specific instance of the novel learning machine. The extension of the overall training method to more-than-one hidden layer architectures is pointed out, as well. A preliminary experimental demonstration is given, outlining how the algorithm works.
KeywordsExpectation maximization partially unsupervised learning co-training adaptive activation function
Unable to display preview. Download preview PDF.
- 1.Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification. Wiley (2001)Google Scholar
- 2.Castelli, I., Trentin, E.: Supervised and Unsupervised Co-Training of Adaptive Activation Functions in Neural Nets. In: Schwenker, F., Trentin, E. (eds.) PSL 2011. LNCS (LNAI), vol. 7081, pp. 52–61. Springer, Heidelberg (2012)Google Scholar
- 3.Bishop, C.M.: Pattern Recognition and Machine Learning. Information Science and Statistics. Springer, Heidelberg (2007)Google Scholar
- 5.Linden, A., Kindermann, J.: Inversion of multilayer nets. In: Proc. of IJCNN 1989, Washington DC, pp. 425–430 (1989)Google Scholar
- 6.Hertz, J.A., Palmer, R.G., Krogh, A.: Introduction to the Theory of Neural Computation. Santa Fe Institute Studies in the Sciences of Complexity. Westview Press (1991)Google Scholar