Asymptotic Convergence of Soft-Constrained Neural Networks for Density Estimation
Abstract
:1. Introduction
2. Materials and Methods
2.1. Review of the Fundamentals of the Training Algorithm
3. Results
3.1. Modeling Capabilities
3.2. Asymptotic Convergence in Probability
4. Conclusions
Funding
Conflicts of Interest
Abbreviations
Probability density function | |
ANN | Artificial neural network |
MLP | Multilayer perceptron |
FFNN | Feed-forward neural network |
SC-NN-4pdf | Soft-constrained neural network for pdfs |
BP | Backpropagation |
References
- Duda, R.O.; Hart, P.E.; Stork, D.G. Pattern Classification, 2nd ed.; Wiley-Interscience: New York, NY, USA, 2000. [Google Scholar]
- Liang, F.; Barron, A. Exact Minimax Strategies for Predictive Density Estimation, Data Compression, and Model Selection. IEEE Trans. Inf. Theory 2004, 50, 2708–2726. [Google Scholar] [CrossRef]
- Beirami, A.; Sardari, M.; Fekri, F. Wireless Network Compression Via Memory-Enabled Overhearing Helpers. IEEE Trans. Wirel. Commun. 2016, 15, 176–190. [Google Scholar] [CrossRef]
- Yang, Z. Machine Learning Approaches to Bioinformatics; World Scientific Publishing Company: Singapore, 2010. [Google Scholar]
- Rabiner, L.R. A tutorial on hidden Markov models and selected applications in speech recognition. Proc. IEEE 1989, 77, 257–286. [Google Scholar] [CrossRef]
- Trentin, E.; Scherer, S.; Schwenker, F. Emotion recognition from speech signals via a probabilistic echo-state network. Pattern Recognit. Lett. 2015, 66, 4–12. [Google Scholar] [CrossRef]
- Bongini, M.; Rigutini, L.; Trentin, E. Recursive Neural Networks for Density Estimation Over Generalized Random Graphs. IEEE Trans. Neural Netw. Learn. Syst. 2018, 29, 5441–5458. [Google Scholar] [CrossRef] [PubMed]
- Trentin, E.; Di Iorio, E. Nonparametric small random networks for graph-structured pattern recognition. Neurocomputing 2018, 313, 14–24. [Google Scholar] [CrossRef]
- Baioletti, M.; Milani, A.; Santucci, V. Learning Bayesian Networks with Algebraic Differential Evolution. In Proceedings of the 15th International Conferenc on Parallel Problem Solving from Nature (PPSN XV), Coimbra, Portugal, 8–12 September 2018; Part II; Lecture Notes in Computer Science. Auger, A., Fonseca, C., Lourenço, N., Machado, P., Paquete, L., Whitley, D., Eds.; Springer: Cham, Switzerland, 2018; Volume 11102, pp. 436–448. [Google Scholar]
- Wang, C.; Xu, C.; Yao, X.; Tao, D. Evolutionary Generative Adversarial Networks. IEEE Trans. Evol. Comput. 2019, 23, 921–934. [Google Scholar] [CrossRef] [Green Version]
- Trentin, E.; Lusnig, L.; Cavalli, F. Parzen neural networks: Fundamentals, properties, and an application to forensic anthropology. Neural Netw. 2018, 97, 137–151. [Google Scholar] [CrossRef] [PubMed]
- Bishop, C.M. Neural Networks for Pattern Recognition; Oxford University Press: Oxford, UK, 1995. [Google Scholar]
- Trentin, E.; Freno, A. Probabilistic Interpretation of Neural Networks for the Classification of Vectors, Sequences and Graphs. In Innovations in Neural Information Paradigms and Applications; Springer: Berlin/Heidelberg, Germany, 2009; pp. 155–182. [Google Scholar]
- Trentin, E.; Bongini, M. Probabilistically Grounded Unsupervised Training of Neural Networks. In Unsupervised Learning Algorithms; Celebi, M., Aydin, K., Eds.; Springer: Cham, Switzerland, 2016; pp. 533–558. [Google Scholar]
- Specht, D. Probabilistic Neural Networks. Neural Netw. 1990, 3, 109–118. [Google Scholar] [CrossRef]
- Modha, D.S.; Fainman, Y. A learning law for density estimation. IEEE Trans. Neural Netw. 1994, 5, 519–523. [Google Scholar] [CrossRef] [PubMed]
- Modha, D.S.; Masry, E. Rate of convergence in density estimation using neural networks. Neural Comput. 1996, 8, 1107–1122. [Google Scholar] [CrossRef]
- Yin, H.; Allinson, N.M. Self-organizing mixture networks for probability density estimation. IEEE Trans. Neural Netw. 2001, 12, 405–411. [Google Scholar] [CrossRef] [PubMed]
- Kohonen, T. Self-organized formation of topologically correct feature maps. Biol. Cybern. 1982, 43, 59–69. [Google Scholar] [CrossRef]
- Vapnik, V.N.; Mukherjee, S. Support Vector Method for Multivariate Density Estimation. In Advances in Neural Information Processing Systems; MIT Press: Cambridge, MA, USA, 2000; pp. 659–665. [Google Scholar]
- Magdon-Ismail, M.; Atiya, A. Density estimation and random variate generation using multilayer networks. IEEE Trans. Neural Netw. 2002, 13, 497–520. [Google Scholar] [CrossRef] [PubMed]
- Trentin, E. Soft-Constrained Nonparametric Density Estimation with Artificial Neural Networks. In Proceedings of the 7th Workshop on Artificial Neural Networks in Pattern Recognition (ANNPR), Ulm, Germany, 28–30 September 2016; Springer: Cham, Switzerland, 2016; pp. 68–79. [Google Scholar]
- Chilinski, P.; Silva, R. Neural Likelihoods via Cumulative Distribution Functions. arXiv 2018, arXiv:1811.00974. [Google Scholar]
- Trentin, E. Maximum-Likelihood Estimation of Neural Mixture Densities: Model, Algorithm, and Preliminary Experimental Evaluation. In Proceedings of the 8th IAPR TC3 Workshop on Artificial Neural Networks in Pattern Recognition, Siena, Italy, 19–21 September 2018; pp. 178–189. [Google Scholar]
- Trentin, E. Soft-Constrained Neural Networks for Nonparametric Density Estimation. Neural Process. Lett. 2018, 48, 915–932. [Google Scholar] [CrossRef]
- Cybenko, G. Approximation by superposition of sigmoidal functions. Math. Control. Signal Syst. 1989, 2, 303–314. [Google Scholar] [CrossRef]
- Hornik, K.; Stinchcombe, M.; White, H. Multilayer feedforward networks are universal approximators. Neural Netw. 1989, 2, 359–366. [Google Scholar] [CrossRef]
- Kolmogorov, A.; Fomin, S. Elementy Teorii Funktsii I Funktsional’nogo Analiza; Nauka (MIR): Moskov, Russia, 1980. [Google Scholar]
- Fukunaga, K. Introduction to Statistical Pattern Recognition, 2nd ed.; Academic Press: San Diego, CA, USA, 1990. [Google Scholar]
- Dekking, F.; Kraaikamp, C.; Lopuhaä, H. A Modern Introduction to Probability and Statistics: Understanding Why and How; Springer: London, UK, 2005. [Google Scholar]
- Gori, M.; Tesi, A. On the Problem of Local Minima in Backpropagation. IEEE Trans. Pattern Anal. Mach. Intell. 1992, 14, 76–86. [Google Scholar] [CrossRef] [Green Version]
- Gori, M.; Tsoi, A.C. Comments on local minima free conditions in multilayer perceptrons. IEEE Trans. Neural Netw. 1998, 9, 1051–1053. [Google Scholar] [CrossRef] [PubMed]
- Parzen, E. Modern Probability Theory and its Applications; John Wiley & Sons: Hoboken, NJ, USA, 1962. [Google Scholar]
© 2020 by the author. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Trentin, E. Asymptotic Convergence of Soft-Constrained Neural Networks for Density Estimation. Mathematics 2020, 8, 572. https://doi.org/10.3390/math8040572
Trentin E. Asymptotic Convergence of Soft-Constrained Neural Networks for Density Estimation. Mathematics. 2020; 8(4):572. https://doi.org/10.3390/math8040572
Chicago/Turabian StyleTrentin, Edmondo. 2020. "Asymptotic Convergence of Soft-Constrained Neural Networks for Density Estimation" Mathematics 8, no. 4: 572. https://doi.org/10.3390/math8040572
APA StyleTrentin, E. (2020). Asymptotic Convergence of Soft-Constrained Neural Networks for Density Estimation. Mathematics, 8(4), 572. https://doi.org/10.3390/math8040572