Information Theoretic Clustering
IEEE Transactions on Pattern Analysis and Machine Intelligence
Neural Networks for Pattern Recognition
Neural Networks for Pattern Recognition
Convergence Properties of the Nelder--Mead Simplex Method in Low Dimensions
SIAM Journal on Optimization
Error Entropy in Classification Problems: A Univariate Data Analysis
Neural Computation
LEGClust—A Clustering Algorithm Based on Layered Entropic Subgraphs
IEEE Transactions on Pattern Analysis and Machine Intelligence
Neural Computation
Adaptive mixtures of local experts
Neural Computation
The Influence of the Risk Functional in Data Classification with MLPs
ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part I
Batch-sequential algorithm for neural networks trained with entropic criteria
ICANN'05 Proceedings of the 15th international conference on Artificial neural networks: formal models and their applications - Volume Part II
Error entropy minimization for LSTM training
ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part I
An error-entropy minimization algorithm for supervised training ofnonlinear adaptive systems
IEEE Transactions on Signal Processing
Correntropy: Properties and Applications in Non-Gaussian Signal Processing
IEEE Transactions on Signal Processing
Single layer complex valued neural network with entropic cost function
ICANN'11 Proceedings of the 21th international conference on Artificial neural networks - Volume Part I
Learning theory approach to minimum error entropy criterion
The Journal of Machine Learning Research
| Hi-index | 0.00 |
This letter focuses on the issue of whether risk functionals derived from information-theoretic principles, such as Shannon or Rényi's entropies, are able to cope with the data classification problem in both the sense of attaining the risk functional minimum and implying the minimum probability of error allowed by the family of functions implemented by the classifier, here denoted by min Pe. The analysis of this so-called minimization of error entropy (MEE) principle is carried out in a single perceptron with continuous activation functions, yielding continuous error distributions. In spite of the fact that the analysis is restricted to single perceptrons, it reveals a large spectrum of behaviors that MEE can be expected to exhibit in both theory and practice. In what concerns the theoretical MEE, our study clarifies the role of the parameters controlling the perceptron activation function (of the squashing type) in often reaching the minimum probability of error. Our study also clarifies the role of the kernel density estimator of the error density in achieving the minimum probability of error in practice.