Learning Topology-preserving Maps Using Self-supervised Backpropagation on a Parallel Machine
نویسنده
چکیده
Self-supervised backpropagation is an unsupervised learning procedure for feedfor-ward networks, where the desired output vector is identical with the input vector. For backpropagation, we are able to use powerful simulators running on parallel machines. Topology-preserving maps, on the other hand, can be developed by a variant of the competitive learning procedure. However, in a degenerate case, self-supervised backpropagation is a version of competitive learning. A simple extension of the cost function of backpropagation leads to a competitive version of self-supervised back-propagation, which can be used to produce topographic maps. We demonstrate the approach applied to the Traveling Salesman Problem (TSP). The algorithm was implemented using the backpropagation simulator (CLONES) on a parallel machine (RAP).
منابع مشابه
Learning Topology-Preserving Maps Using Self-Supervised Backpropagation
Self-supervised backpropagation is an unsupervised learning procedure for feedforward networks , where the desired output vector is identical with the input vector. For backpropagation, we are able to use powerful simulators running on parallel machines. Topology-preserving maps, on the other hand, can be developed by a variant of the competitive learning procedure. However , in a degenerate ca...
متن کاملA Geometry Preserving Kernel over Riemannian Manifolds
Abstract- Kernel trick and projection to tangent spaces are two choices for linearizing the data points lying on Riemannian manifolds. These approaches are used to provide the prerequisites for applying standard machine learning methods on Riemannian manifolds. Classical kernels implicitly project data to high dimensional feature space without considering the intrinsic geometry of data points. ...
متن کاملDynamic Cell Structures
Dynamic Cell Structures (DCS) represent a family of artificial neural architectures suited both for unsupervised and supervised learning. They belong to the recently [Martinetz94] introduced class of Topology Representing Networks (TRN) which build perlectly topology preserving feature maps. DCS empI'oy a modified Kohonen learning rule in conjunction with competitive Hebbian learning. The Kohon...
متن کاملPattern Analysis with Layered Self-Organizing Maps
1. Abstract Abstract— This paper defines a new learning architecture, Layered Self-Organizing Maps (LSOMs), that uses the SOM and supervised-SOM learning algorithms. The architecture is validated with the MNIST database of hand-written digit images. LSOMs are similar to convolutional neural nets (covnets) in the way they sample data, but different in the way they represent features and learn. L...
متن کاملSupervised Learning for Automatic Classification of Documents using Self-Organizing Maps
Automatic Document Classification that corresponds with user-predefined classes is a challenging and widely researched area. Self-Organizing Maps (SOM) are unsupervised Artificial Neural Networks (ANN) which are mathematically characterized by transforming high-dimensional data into two-dimension representation, enabling automatic clustering of the input, while preserving higher order topology....
متن کامل