Please use this identifier to cite or link to this item:
Title: An analytic layer-wise deep learning framework with applications to robotics
Authors: Nguyen, Huu-Thiet
Cheah, Chien Chern
Toh, Kar-Ann
Keywords: Engineering::Electrical and electronic engineering
Issue Date: 2022
Source: Nguyen, H., Cheah, C. C. & Toh, K. (2022). An analytic layer-wise deep learning framework with applications to robotics. Automatica, 135, 110007-.
Project: A1883c0008
Journal: Automatica
Abstract: Deep learning (DL) has achieved great success in many applications, but it has been less well analyzed from the theoretical perspective. The unexplainable success of black-box DL models has raised questions among scientists and promoted the emergence of the field of explainable artificial intelligence (XAI). In robotics, it is particularly important to deploy DL algorithms in a predictable and stable manner as robots are active agents that need to interact safely with the physical world. This paper presents an analytic deep learning framework for fully connected neural networks, which can be applied for both regression problems and classification problems. Examples for regression and classification problems include online robot control and robot vision. We present two layer-wise learning algorithms such that the convergence of the learning systems can be analyzed. Firstly, an inverse layer-wise learning algorithm for multilayer networks with convergence analysis for each layer is presented to understand the problems of layer-wise deep learning. Secondly, a forward progressive learning algorithm where the deep networks are built progressively by using single hidden layer networks is developed to achieve better accuracy. It is shown that the progressive learning method can be used for fine-tuning of weights from convergence point of view. The effectiveness of the proposed framework is illustrated based on classical benchmark recognition tasks using the MNIST and CIFAR-10 datasets and the results show a good balance between performance and explainability. The proposed method is subsequently applied for online learning of robot kinematics and experimental results on kinematic control of UR5e robot with unknown model are presented.
ISSN: 0005-1098
DOI: 10.1016/j.automatica.2021.110007
Schools: School of Electrical and Electronic Engineering 
Rights: © 2021 Elsevier Ltd. All rights reserved.
Fulltext Permission: none
Fulltext Availability: No Fulltext
Appears in Collections:EEE Journal Articles

Citations 20

Updated on Jun 11, 2024

Web of ScienceTM
Citations 50

Updated on Oct 26, 2023

Page view(s)

Updated on Jun 13, 2024

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.