Zhang W, Wu QMJ, Yang Y, Akilan T. Multimodel Feature Reinforcement Framework Using Moore-Penrose Inverse for Big Data Analysis.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2021;
32:5008-5021. [PMID:
33021948 DOI:
10.1109/tnnls.2020.3026621]
[Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/11/2023]
Abstract
Fully connected representation learning (FCRL) is one of the widely used network structures in multimodel image classification frameworks. However, most FCRL-based structures, for instance, stacked autoencoder encode features and find the final cognition with separate building blocks, resulting in loosely connected feature representation. This article achieves a robust representation by considering a low-dimensional feature and the classifier model simultaneously. Thus, a new hierarchical subnetwork-based neural network (HSNN) is proposed in this article. The novelties of this framework are as follows: 1) it is an iterative learning process, instead of stacking separate blocks to obtain the discriminative encoding and the final classification results. In this sense, the optimal global features are generated; 2) it applies Moore-Penrose (MP) inverse-based batch-by-batch learning strategy to handle large-scale data sets, so that large data set, such as Place365 containing 1.8 million images, can be processed effectively. The experimental results on multiple domains with a varying number of training samples from ∼ 1 K to ∼ 2 M show that the proposed feature reinforcement framework achieves better generalization performance compared with most state-of-the-art FCRL methods.
Collapse