Chen C L Philip, Liu Zhulin, Feng Shuang
IEEE Trans Neural Netw Learn Syst. 2019 Apr;30(4):1191-1204. doi: 10.1109/TNNLS.2018.2866622. Epub 2018 Sep 10.
After a very fast and efficient discriminative broad learning system (BLS) that takes advantage of flatted structure and incremental learning has been developed, here, a mathematical proof of the universal approximation property of BLS is provided. In addition, the framework of several BLS variants with their mathematical modeling is given. The variations include cascade, recurrent, and broad-deep combination structures. From the experimental results, the BLS and its variations outperform several exist learning algorithms on regression performance over function approximation, time series prediction, and face recognition databases. In addition, experiments on the extremely challenging data set, such as MS-Celeb-1M, are given. Compared with other convolutional networks, the effectiveness and efficiency of the variants of BLS are demonstrated.
在开发了一种利用扁平结构和增量学习的非常快速且高效的判别式广义学习系统（BLS）之后，本文给出了BLS通用逼近特性的数学证明。此外，还给出了几种BLS变体及其数学建模的框架。这些变体包括级联、递归和广义深度组合结构。从实验结果来看，BLS及其变体在函数逼近、时间序列预测和人脸识别数据库的回归性能方面优于几种现有的学习算法。此外，还给出了在极具挑战性的数据集（如MS-Celeb-1M）上的实验。与其他卷积网络相比，证明了BLS变体的有效性和效率。
