Efficient Inverse-Free Incremental and Decremental Algorithms for Multiple Hidden Nodes in Extreme Learning Machine

04/27/2020
by   Hufei Zhu, et al.
0

The inverse-free extreme learning machine (ELM) algorithm proposed in [4] was based on an inverse-free algorithm to compute the regularized pseudo-inverse, which was deduced from an inverse-free recursive algorithm to update the inverse of a Hermitian matrix. Before that recursive algorithm was applied in [4], its improved version had been utilized in previous literatures [9], [10]. Accordingly from the improved recursive algorithm [9], [10], several efficient inverse-free algorithms for ELM were proposed in [13] to reduce the computational complexity. In this paper, we propose two inverse-free algorithms for ELM with Tikhonov regularization, which can increase multiple hidden nodes in an iteration. On the other hand, we also propose two efficient decremental learning algorithms for ELM with Tikhonov regularization, which can remove multiple redundant nodes in an iteration.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/12/2019

Efficient Inverse-Free Algorithms for Extreme Learning Machine Based on the Recursive Matrix Inverse and the Inverse LDL' Factorization

The inverse-free extreme learning machine (ELM) algorithm proposed in [4...
research
12/31/2019

Efficient Decremental Learning Algorithms for Broad Learning System

The decremented learning algorithms are required in machine learning, to...
research
12/10/2019

Inverse LDM' and LU Factorizations of a Partitioned Matrix with the Square-root and Division Free Version for V-BLAST

This letter proposes the inverse LDM' and LU factorizations of a matrix ...
research
05/30/2019

Scaling Up Quasi-Newton Algorithms: Communication Efficient Distributed SR1

In this paper, we present a scalable distributed implementation of the s...
research
05/14/2020

Efficient and Stable Algorithms to Extend Greville's Method to Partitioned Matrices Based on Inverse Cholesky Factorization

Greville's method has been utilized in (Broad Learn-ing System) BLS to p...
research
05/21/2021

Low-Memory Implementations of Ridge Solutions for Broad Learning System with Incremental Learning

The existing low-memory BLS implementation proposed recently avoids the ...
research
10/17/2019

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 reducin...

Please sign up or login with your details

Forgot password? Click here to reset