Broad Learning System: An Effective and Efficient Incremental Learning System Without the Need for Deep Architecture

• Published in: IEEE transaction on neural networks and learning systems Vol. 29; no. 1; pp. 10 - 24
• Main Authors: Chen, C. L. Philip, Liu, Zhulin
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.01.2018; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithm design and analysis; Algorithms; Approximation algorithms; Artificial neural networks; Big data; big data modeling; broad learning system (BLS); deep learning; Feature extraction; Filters; Heuristic algorithms; incremental learning; Learning algorithms; Learning systems; Machine learning; Model reduction; Neural networks; Nodes; NorB protein; Object recognition; Pattern recognition; random vector functional-link neural networks (RVFLNN); Retraining; single layer feedforward neural networks (SLFN); Singular value decomposition; singular value decomposition (SVD); Training
• ISSN: 2162-237X; 2162-2388; 2162-2388
• DOI: 10.1109/TNNLS.2017.2716952

Broad Learning System (BLS) that aims to offer an alternative way of learning in deep structure is proposed in this paper. Deep structure and learning suffer from a time-consuming training process because of a large number of connecting parameters in filters and layers. Moreover, it encounters a complete retraining process if the structure is not sufficient to model the system. The BLS is established in the form of a flat network, where the original inputs are transferred and placed as "mapped features" in feature nodes and the structure is expanded in wide sense in the "enhancement nodes." The incremental learning algorithms are developed for fast remodeling in broad expansion without a retraining process if the network deems to be expanded. Two incremental learning algorithms are given for both the increment of the feature nodes (or filters in deep structure) and the increment of the enhancement nodes. The designed model and algorithms are very versatile for selecting a model rapidly. In addition, another incremental learning is developed for a system that has been modeled encounters a new incoming input. Specifically, the system can be remodeled in an incremental way without the entire retraining from the beginning. Satisfactory result for model reduction using singular value decomposition is conducted to simplify the final structure. Compared with existing deep neural networks, experimental results on the Modified National Institute of Standards and Technology database and NYU NORB object recognition dataset benchmark data demonstrate the effectiveness of the proposed BLS.