Integration of inductive learning and neural networks for multi-objective FMS scheduling

1998 ◽  
Vol 36 (9) ◽  
pp. 2497-2509 ◽  
Author(s):  
C.-O. Kim ◽  
H.-S. Min ◽  
Y. Yih
Keyword(s):  
Neural Networks ◽  
Inductive Learning ◽  
Multi Objective ◽  
Fms Scheduling

Efficient fog prediction with multi-objective evolutionary neural networks

2018 ◽  
Vol 70 ◽  
pp. 347-358 ◽  
Author(s):  
A.M. Durán-Rosal ◽  
J.C. Fernández ◽  
C. Casanova-Mateo ◽  
J. Sanz-Justo ◽  
S. Salcedo-Sanz ◽  
...  
Keyword(s):  
Neural Networks ◽  
Multi Objective ◽  
Evolutionary Neural Networks ◽  
Fog Prediction

A Multi-Objective Evolutionary Approach Based on Graph-in-Graph for Neural Architecture Search of Convolutional Neural Networks

2021 ◽  
pp. 2150035
Author(s):  
Yu Xue ◽  
Pengcheng Jiang ◽  
Ferrante Neri ◽  
Jiayu Liang
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Network Structure ◽  
Ad Hoc ◽  
Network Design Problem ◽  
Multi Objective ◽  
Neural Architecture ◽  
Mutation Operators ◽  
Small Structure ◽  
High Flexibility

With the development of deep learning, the design of an appropriate network structure becomes fundamental. In recent years, the successful practice of Neural Architecture Search (NAS) has indicated that an automated design of the network structure can efficiently replace the design performed by human experts. Most NAS algorithms make the assumption that the overall structure of the network is linear and focus solely on accuracy to assess the performance of candidate networks. This paper introduces a novel NAS algorithm based on a multi-objective modeling of the network design problem to design accurate Convolutional Neural Networks (CNNs) with a small structure. The proposed algorithm makes use of a graph-based representation of the solutions which enables a high flexibility in the automatic design. Furthermore, the proposed algorithm includes novel ad-hoc crossover and mutation operators. We also propose a mechanism to accelerate the evaluation of the candidate solutions. Experimental results demonstrate that the proposed NAS approach can design accurate neural networks with limited size.

Sign in / Sign up

Export Citation Format

Share Document