Results 231 to 240 of about 8,717,007 (282)
Dual-Layer Kernel Extreme Learning Machine for Action Recognition
Abstract In this paper, we propose a simple yet effective method for video based action recognition referred to as dual-layer kernel extreme learning machine (DKELM). Our approach takes advantages of both early and late fusion techniques into a unified framework.
Tam V Nguyen, Bilal Mirza
exaly +4 more sources
Some of the next articles are maybe not open access.
Related searches:
Related searches:
Multiple Kernel Extreme Learning Machine
Neurocomputing, 2015Extreme learning machine (ELM) has been an important research topic over the last decade due to its high efficiency, easy-implementation, unification of classification and regression, and unification of binary and multi-class learning tasks. Though integrating these advantages, existing ELM algorithms pay little attention to optimizing the choice of ...
Xinwang Liu, Lei Wang, Guang-Bin Huang
exaly +4 more sources
Infinite Kernel Extreme Learning Machine
This paper addresses the analysis of the problem of combining Infinite Kernel Learning (IKL) approach and Extreme Learning Machine (ELM) structure. ELM represents a novel and promising alternative to Neural Networks, for its simplicity in implementation and high efficiency, especially concerning convergence and generalization performance.
Elisa Marcelli, Renato De Leone
openaire +3 more sources
On the Kernel Extreme Learning Machine Speedup
Pattern Recognition Letters, 2015We propose an approximate solution for the kernel Extreme Learning Machine.The proposed method reduces the computational and memory costs of kELM.The proposed approach achieves satisfactory classification performance. In this paper, we describe an approximate method for reducing the time and memory complexities of the kernel Extreme Learning Machine ...
Moncef Gabbouj, Alexandros Iosifidis
exaly +3 more sources
Two-stage Unsupervised Multiple Kernel Extreme Learning Machine
As a powerful learning tool, Extreme Learning Machine (ELM) shows its merits in classification, regression and clustering by offering both high prediction accuracy and high learning speed. Among numerous ELM varieties, multiple kernel ELM draws intensive attention from researchers because it can leverage information from multiple heterogeneous sources,
Guohan Zhao +3 more
openaire +3 more sources

