Fine-tuning Deep Belief Networks using Harmony Search
作者： João Paulo Papa , Walter Scheirer , David Daniel Cox
DOI: 10.1016/J.ASOC.2015.08.043
关键词:
摘要: Graphical abstractDisplay Omitted In this paper, we deal with the problem of Deep Belief Networks (DBNs) parameters fine-tuning by means a fast meta-heuristic approach named Harmony Search (HS). Although such deep learning-based technique has been widely used in last years, more detailed studies about how to set its may not be observed literature. We have shown can obtain accurate results comparing HS against several variants, random search and two variants well-known Hyperopt library. The experimental were carried out public datasets considering task binary image reconstruction, three DBN learning algorithms layers.
acm.org
fapesp.br
elsevier.com
sci-hub.se 参考文章(36)
Geoffrey E. Hinton, A Practical Guide to Training Restricted Boltzmann Machines Neural Networks: Tricks of the Trade (2nd ed.). pp. 599- 619 ,(2012) , 10.1007/978-3-642-35289-8_32
Zong Woo Geem, Music-Inspired Harmony Search Algorithm: Theory and Applications Music-Inspired Harmony Search Algorithm: Theory and Applications 1st. pp. 206- 206 ,(2009)
Philemon Brakel, Sander Dieleman, Benjamin Schrauwen, Training Restricted Boltzmann Machines with Multi-tempering: Harnessing Parallelization Artificial Neural Networks and Machine Learning – ICANN 2012. ,vol. 7553, pp. 92- 99 ,(2012) , 10.1007/978-3-642-33266-1_12
Takashi Kuremoto, Shinsuke Kimura, Kunikazu Kobayashi, Masanao Obayashi, Time Series Forecasting Using Restricted Boltzmann Machine Communications in Computer and Information Science. pp. 17- 22 ,(2012) , 10.1007/978-3-642-31837-5_3
DAVID H. ACKLEY, GEOFFREY E. HINTON, TERRENCE J. SEJNOWSKI, A learning algorithm for Boltzmann machines Connectionist models and their implications: readings from cognitive science. pp. 635- 649 ,(1988) , 10.1016/B978-0-08-051581-6.50053-2
Neural Networks: Tricks of the Trade Springer. ,(2012) , 10.1007/978-3-642-35289-8
Frank Wilcoxon, Individual Comparisons by Ranking Methods Springer Series in Statistics. ,vol. 1, pp. 196- 202 ,(1992) , 10.1007/978-1-4612-4380-9_16
Ruhi Sarikaya, Geoffrey E. Hinton, Anoop Deoras, Application of Deep Belief Networks for natural language understanding IEEE Transactions on Audio, Speech, and Language Processing. ,vol. 22, pp. 778- 784 ,(2014) , 10.1109/TASLP.2014.2303296
Erez Levy, Omid E. David, Nathan S. Netanyahu, Genetic algorithms and deep learning for automatic painter classification genetic and evolutionary computation conference. pp. 1143- 1150 ,(2014) , 10.1145/2576768.2598287
Dexuan Zou, Liqun Gao, Jianhua Wu, Steven Li, Yang Li, A novel global harmony search algorithm for reliability problems Computers & Industrial Engineering. ,vol. 58, pp. 307- 316 ,(2010) , 10.1016/J.CIE.2009.11.003