Open Access

ARTICLE

Hyperparameter Tuning for Deep Neural Networks Based Optimization Algorithm

D. Vidyabharathi^1,*, V. Mohanraj²
1 Sona College of Technology, Computer Science and Engineering, Salem, 636005, India
2 Sona College of Technology, Information Technology, Salem, 636005, India
* Corresponding Author: D. Vidyabharathi. Email: vidyabharathid9764@gmail.com

Intelligent Automation & Soft Computing https://doi.org/10.32604/iasc.2023.032255

Received 11 May 2022; Accepted 08 August 2023; Published online 10 January 2023

Abstract

For training the present Neural Network (NN) models, the standard technique is to utilize decaying Learning Rates (LR). While the majority of these techniques commence with a large LR, they will decay multiple times over time. Decaying has been proved to enhance generalization as well as optimization. Other parameters, such as the network’s size, the number of hidden layers, dropouts to avoid overfitting, batch size, and so on, are solely based on heuristics. This work has proposed Adaptive Teaching Learning Based (ATLB) Heuristic to identify the optimal hyperparameters for diverse networks. Here we consider three architectures Recurrent Neural Networks (RNN), Long Short Term Memory (LSTM), Bidirectional Long Short Term Memory (BiLSTM) of Deep Neural Networks for classification. The evaluation of the proposed ATLB is done through the various learning rate schedulers Cyclical Learning Rate (CLR), Hyperbolic Tangent Decay (HTD), and Toggle between Hyperbolic Tangent Decay and Triangular mode with Restarts (T-HTR) techniques. Experimental results have shown the performance improvement on the 20Newsgroup, Reuters Newswire and IMDB dataset.

---

Keywords

Deep learning; deep neural network (DNN); learning rates (LR); recurrent neural network (RNN); cyclical learning rate (CLR); hyperbolic tangent decay (HTD); toggle between hyperbolic tangent decay and triangular mode with restarts (T-HTR); teaching learning based optimization (TLBO)

---