Deep Stochastic Configuration Networks with Universal Approximation Property
arXiv:1702.05639
Abstract
This paper develops a randomized approach for incrementally building deep neural networks, where a supervisory mechanism is proposed to constrain the random assignment of the weights and biases, and all the hidden layers have direct links to the output layer. A fundamental result on the universal approximation property is established for such a class of randomized leaner models, namely deep stochastic configuration networks (DeepSCNs). A learning algorithm is presented to implement DeepSCNs with either specific architecture or self-organization. The read-out weights attached with all direct links from each hidden layer to the output layer are evaluated by the least squares method. Given a set of training examples, DeepSCNs can speedily produce a learning representation, that is, a collection of random basis functions with the cascaded inputs together with the read-out weights. An empirical study on a function approximation is carried out to demonstrate some properties of the proposed deep learner model.
arXiv commentTo appear in the Proceedings of IJCNN 2018
References in corpus (7)
- Deep Learning in Neural Networks: An Overview
- Stochastic Configuration Networks: Fundamentals and Algorithms
- Provable Bounds for Learning Some Deep Representations
- The Power of Depth for Feedforward Neural Networks
- Deep Neural Networks with Random Gaussian Weights: A Universal Classification Strategy?
- Approximation with Random Bases: Pro et Contra
- A Powerful Generative Model Using Random Weights for the Deep Image Representation