Performance comparison of training algorithms for semi-supervised discriminative language modeling

2012 ◽  
Author(s):  
Erinç Dikici ◽  
Arda Çelebi ◽  
Murat Saraçlar
Keyword(s):  
Language Modeling ◽  
Performance Comparison ◽  
Training Algorithms

scholarly journals Performance Comparison of ANN Training Algorithms for Hysteresis Determination in LTE networks

2019 ◽  
Vol 1378 ◽  
pp. 042094
Author(s):  
E E Ekong ◽  
A A Adewale ◽  
A Ben-Obaje ◽  
A M Alalade ◽  
C N Ndujiuba
Keyword(s):  
Performance Comparison ◽  
Training Algorithms ◽  
Lte Networks

Performance comparison of neural network training algorithms in modeling of bimodal drug delivery

2006 ◽  
Vol 327 (1-2) ◽  
pp. 126-138 ◽  
Author(s):  
A. Ghaffari ◽  
H. Abdollahi ◽  
M.R. Khoshayand ◽  
I. Soltani Bozchalooi ◽  
A. Dadgar ◽  
...  
Keyword(s):  
Neural Network ◽  
Drug Delivery ◽  
Performance Comparison ◽  
Training Algorithms ◽  
Neural Network Training ◽  
Network Training

A study on performance of MHDA in training MLPs

2019 ◽  
Vol 36 (6) ◽  
pp. 1820-1834 ◽  
Author(s):  
Sree Ranjini K.S.
Keyword(s):  
Network Models ◽  
Performance Comparison ◽  
Data Sets ◽  
Training Algorithms ◽  
Neural Network Models ◽  
Content Type ◽  
Dragonfly Algorithm ◽  
Deterministic Algorithms ◽  
Mlp Model ◽  
Optimal Set

Purpose In recent years, the application of metaheuristics in training neural network models has gained significance due to the drawbacks of deterministic algorithms. This paper aims to propose the use of a recently developed “memory based hybrid dragonfly algorithm” (MHDA) for training multi-layer perceptron (MLP) model by finding the optimal set of weight and biases. Design/methodology/approach The efficiency of MHDA in training MLPs is evaluated by applying it to classification and approximation benchmark data sets. Performance comparison between MHDA and other training algorithms is carried out and the significance of results is proved by statistical methods. The computational complexity of MHDA trained MLP is estimated. Findings Simulation result shows that MHDA can effectively find the near optimum set of weight and biases at a higher convergence rate when compared to other training algorithms. Originality/value This paper presents MHDA as an alternative optimization algorithm for training MLP. MHDA can effectively optimize set of weight and biases and can be a potential trainer for MLPs.

Sign in / Sign up

Export Citation Format

Share Document