Redirigiendo al acceso original de articulo en 17 segundos...
Inicio  /  Applied Sciences  /  Vol: 12 Par: 15 (2022)  /  Artículo
ARTÍCULO
TITULO

Improving Deep Mutual Learning via Knowledge Distillation

Achmad Lukman and Chuan-Kai Yang    

Resumen

Knowledge transfer has become very popular in recent years, and it is either based on a one-way transfer method used with knowledge distillation or based on a two-way knowledge transfer implemented by deep mutual learning, while both of them adopt a teacher?student paradigm. A one-way based method is more simple and compact because it only involves an untrained low-capacity student and a high-capacity teacher network in the knowledge transfer process. In contrast, a two-way based method requires more training costs because it involves two or more low-cost network capacities from scratch simultaneously to obtain better accuracy results for each network. In this paper, we propose two new approaches, namely full deep distillation mutual learning (FDDML) and half deep distillation mutual learning (HDDML), and improve convolutional neural network performance. These approaches work with three losses by using variations of existing network architectures, and the experiments have been conducted on three public benchmark datasets. We test our method on some existing KT task methods, showing its performance over related methods.

 Artículos similares

       
 
Juan C. Gutiérrez-Diez, Ana M. Castañón and Marc Bascompta    
The sustainable development of mining processes requires a deep knowledge of the effectiveness of mining equipment and is quite complex to analyze due to the intrinsic characteristics of the mining industry. In this regard, its measurement and control ca... ver más
Revista: Applied Sciences

 
Jingyi Hu, Junfeng Guo, Zhiyuan Rui and Zhiming Wang    
To solve the problem that noise seriously affects the online monitoring of parts signals of outdoor machinery, this paper proposes a signal reconstruction method integrating deep neural network and compression sensing, called ADMM-1DNet, and gives a deta... ver más
Revista: Applied Sciences

 
Yanjun Li, Takaaki Yoshimura, Yuto Horima and Hiroyuki Sugimori    
The detection of coronary artery stenosis is one of the most important indicators for the diagnosis of coronary artery disease. However, stenosis in branch vessels is often difficult to detect using computer-aided systems and even radiologists because of... ver más
Revista: Algorithms

 
MohammadHossein Reshadi, Wen Li, Wenjie Xu, Precious Omashor, Albert Dinh, Scott Dick, Yuntong She and Michael Lipsett    
Anomaly detection in data streams (and particularly time series) is today a vitally important task. Machine learning algorithms are a common design for achieving this goal. In particular, deep learning has, in the last decade, proven to be substantially ... ver más
Revista: Algorithms

 
Eyad K. Sayhood, Nisreen S. Mohammed, Salam J. Hilo and Salih S. Salih    
This paper presents comprehensive empirical equations to predict the shear strength capacity of reinforced concrete deep beams, with a focus on improving the accuracy of existing codes. Analyzing 198 deep beams imported from 15 existing investigations, t... ver más
Revista: Infrastructures