Feature Selection with L1 Regularization in Formal Neurons

Designing classifiers on high-dimensional learning data sets is an important task that appears in artificial intelligence applications. Designing classifiers for high-dimensional data involves learning hierarchical neural networks combined with feature selection. Feature selection aims to omit features that are unnecessary for a given problem. Feature selection in formal meurons can be achieved by minimizing convex and picewise linear (CPL) criterion functions with L-1 regularization. Minimizing CPL criterion functions can be associated with computations on a finite number of vertices in the parameter space.