论文信息 - Reducing the Computational Complexity of Pseudoinverse for the Incremental Broad Learning System on Added Inputs

Reducing the Computational Complexity of Pseudoinverse for the Incremental Broad Learning System on Added Inputs

In this brief, we improve the Broad Learning System (BLS) [7] by reducing the computational complexity of the incremental learning for added inputs. We utilize the inverse of a sum of matrices in [8] to improve a step in the pseudoinverse of a row-partitioned matrix. Accordingly we propose two fast algorithms for the cases of q > k and q k, the proposed algorithm computes only a k * k matrix inverse, instead of a q * q matrix inverse in the existing algorithm. Accordingly it can reduce the complexity dramatically. Our simulations, which follow those for Table V in [7], show that the proposed algorithm and the existing algorithm achieve the same testing accuracy, while the speedups in BLS training time of the proposed algorithm over the existing algorithm are 1.24 - 1.30.

Hufei Zhu | Chenghao Wei

[1] Dejan J. Sobajic,et al. Learning and generalization characteristics of the random vector Functional-link net , 1994, Neurocomputing.

[2] Lawrence D. Jackel,et al. Handwritten Digit Recognition with a Back-Propagation Network , 1989, NIPS.

[3] Isabelle Guyon,et al. Neural Network Recognizer for Hand-Written Zip Code Digits , 1988, NIPS.

[4] S. R. Searle,et al. On Deriving the Inverse of a Sum of Matrices , 1981 .

[5] Allan Pinkus,et al. Multilayer Feedforward Networks with a Non-Polynomial Activation Function Can Approximate Any Function , 1991, Neural Networks.

[6] C. L. Philip Chen,et al. Broad Learning System: An Effective and Efficient Incremental Learning System Without the Need for Deep Architecture , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[7] C. L. Philip Chen,et al. A rapid learning and dynamic stepwise updating algorithm for flat neural networks and the application to time-series prediction , 1999, IEEE Trans. Syst. Man Cybern. Part B.