Decision Manifolds: Classification Inspired by Self-Organization
نویسندگان
چکیده
We present a classifier algorithm that approximates the decision surface of labeled data by a patchwork of separating hyperplanes. The hyperplanes are arranged in a way inspired by how Self-Organizing Maps are trained. We take advantage of the fact that the boundaries can often be approximated by linear ones connected by a low-dimensional nonlinear manifold. The resulting classifier allows for a voting scheme that averages over neighboring hyperplanes. Our algorithm is computationally efficient both in terms of training and classification. Further, we present a model selection framework for estimation of the paratmeters of the classification boundary, and show results for artificial and real-world data sets.
منابع مشابه
Multiple point of self-transverse immesions of certain manifolds
In this paper we will determine the multiple point manifolds of certain self-transverse immersions in Euclidean spaces. Following the triple points, these immersions have a double point self-intersection set which is the image of an immersion of a smooth 5-dimensional manifold, cobordant to Dold manifold $V^5$ or a boundary. We will show there is an immersion of $S^7times P^2$ in $mathbb{R}^{1...
متن کاملExclusionary Decision Making in Tehran Metropolitan Region- Complexity, Self organization and Power of Action
Viewing urban areas as webs of complex, interwoven networks, this article aims to analyze the decision-making process and its outcomes in Tehran metropolitan region. To do so, first the theoretical basis of complexity in urban life and its implications for planning have been reviewed. Using the main notion of power of action i.e. agency, and through creating the network of actors and their rela...
متن کاملDynamic self-organised neural network inspired by the immune algorithm for financial time series prediction and medical data classification
متن کامل
Negative Selection Based Data Classification with Flexible Boundaries
One of the most important artificial immune algorithms is negative selection algorithm, which is an anomaly detection and pattern recognition technique; however, recent research has shown the successful application of this algorithm in data classification. Most of the negative selection methods consider deterministic boundaries to distinguish between self and non-self-spaces. In this paper, two...
متن کاملLow dimensional flat manifolds with some classes of Finsler metric
Flat Riemannian manifolds are (up to isometry) quotient spaces of the Euclidean space R^n over a Bieberbach group and there are an exact classification of of them in 2 and 3 dimensions. In this paper, two classes of flat Finslerian manifolds are stuided and classified in dimensions 2 and 3.
متن کامل