Optimal hyperparameter tuning of convolutional neural networks based on the parameter-setting-free harmony search algorithm

Optik ◽  
2018 ◽  
Vol 172 ◽  
pp. 359-367 ◽  
Author(s):  
Woo-Young Lee ◽  
Seung-Min Park ◽  
Kwee-Bo Sim
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Search Algorithm ◽  
Harmony Search ◽  
Harmony Search Algorithm ◽  
Parameter Setting

scholarly journals Advanced Parameter-Setting-Free Harmony Search Algorithm

2020 ◽  
Vol 10 (7) ◽  
pp. 2586
Author(s):  
Yong-Woon Jeong ◽  
Seung-Min Park ◽  
Zong Woo Geem ◽  
Kwee-Bo Sim
Keyword(s):  
Search Algorithm ◽  
Harmony Search ◽  
Harmony Search Algorithm ◽  
Parameter Setting ◽  
Additional Memory ◽  
Memory Utilization ◽  
Number Of Iterations

In this paper, we propose an advanced parameter-setting-free (PSF) scheme to solve the problem of setting the parameters for the harmony search (HS) algorithm. The use of the advanced PSF method solves the problems of the conventional PSF scheme that results from a large number of iterations and shows good results compared to fixing the parameters required for the HS algorithm. In addition, unlike the conventional PSF method, the advanced PSF method does not use additional memory. We expect the advanced PSF method to be applicable to various fields that use the HS algorithm because it reduces the memory utilization for operations while obtaining better results than conventional PSF schemes.

Generating a Adhesive Nozzle Path by the Parameter-Setting-Free Harmony Search Algorithm for a Shoe-Upper Assembly Process

2018 ◽  
Vol 28 (1) ◽  
pp. 49-56
Author(s):  
Woo-Young Lee ◽  
Sung-Won Lee ◽  
Seung-Min Park ◽  
Tae-Hyoung Kim ◽  
Zong-Woo Geem ◽  
...  
Keyword(s):  
Search Algorithm ◽  
Harmony Search ◽  
Harmony Search Algorithm ◽  
Assembly Process ◽  
Parameter Setting

scholarly journals Application of Harmony Search algorithm with Neural Networks Solving MTHD Problem in Multi l evel inverter with Alterable DC links

2016 ◽  
Vol 8 (1) ◽  
pp. 12-28 ◽  
Author(s):  
Mohammad Reza Jannati Oskuee ◽  
◽  
Rahim Shamsi Varzeghan ◽  
Alireza Eyvaz i zadeh Khosroshahi ◽  
Sajad Najafi Ravadanegh ◽  
...  
Keyword(s):  
Neural Networks ◽  
Search Algorithm ◽  
Harmony Search ◽  
Harmony Search Algorithm

A Self-Adaptive Harmony Search Algorithm for Unconstrained Optimization Problems

2014 ◽  
Vol 596 ◽  
pp. 192-195
Author(s):  
Ping Zhang ◽  
Peng Sun ◽  
Yi Ning Zhang ◽  
Guo Jun Li
Keyword(s):  
Unconstrained Optimization ◽  
Optimization Problems ◽  
Search Algorithm ◽  
Harmony Search ◽  
Harmony Search Algorithm ◽  
Parameter Setting ◽  
Unconstrained Optimization Problems ◽  
Suitable Parameter ◽  
Parameter Values ◽  
Self Adaptive

Recently, a new meta-heuristic optimization algorithm–harmony search (HS) was developed, which imitates the behaviors of music improvisation. Although several variants and an increasing number of applications have appeared, one of its main difficulties is how to select suitable parameter values. In this paper, a self-adaptive harmony search algorithm (SaHS) proposed. In this algorithm, we design a new parameter setting strategy to directly tune the parameters in the search process, and balance the process of exploitation and exploration. Finally, we use SaHS to solve unconstrained optimization problems so as to profoundly study and analyze the performance of the SaHS. The results show that the SaHS has better convergence accuracy than the other three harmony search algorithms.

Sign in / Sign up

Export Citation Format

Share Document