0% Complete
Home
/
14th International Conference on Computer and Knowledge Engineering
Evolutionary Approach to GAN Hyperparameter Tuning: Minimizing Discriminator and Generator Loss Functions
Authors :
Sajad Haghzad Klidbary
1
Anahita Babaei
2
Ramin Ghorbani
3
1- University of Zanjan
2- university of za
3- University of Zanjan
Keywords :
Generative Adversarial Networks (GAN)،Optimization،Genetic Algorithm (GA)،d_loss،g_loss،MNIST
Abstract :
Image Reconstruction has always been among machine vision’s challenging topics. One of image restoration’s most challenging is to fill the damaged area after deleting, it in a visually acceptable way. The beginning of image reconstruction goes back to the last five decades, but due to the ineffectiveness of the basic methods, new methods have been offered. In the field of image restoration, GAN or Generative Adversarial Networks can be very useful due to the high similarity between the generated data and the training data. In this paper, by presenting an algorithm based on these networks, we try to increase the accuracy of the image restoration process. The GAN algorithm's accuracy is related to the correct selection of parameters. Using trial and error methods to find parameters is time-consuming and has problems. In this paper, the optimal parameters of the GAN algorithm have been used by providing suitable coding for the genetic algorithm. The simulation results represent that the proposed GA has notable performance. The best results give a minimum value of about 0.16 for the discriminator loss function and 0 for the generator loss function.
Papers List
List of archived papers
Classification of Audio Streaming in Network Traffic Based on Machine Learning Methods
Mohammad Nikbakht - Mehdi Teimouri
Efficient Vision Transformer for Accurate Traffic Sign Detection
Javad Mirzapour Kaleybar - Hooman Khaloo - Avaz Naghipour
A Smart Electrochemical Biosensor for Arsenic Detection in Water
Keyvan Asefpour Vakilian
Predicting cascading failure with machine learning methods in the interdependent networks
Mohamad Hossein Maghsoodi - Mohamad Khansari
FarCQA: A Farsi Community Dataset for Question Classification and Answer Selection
Saba Emami - Maedeh Mosharraf
A Hybrid Echo State Network for Hypercomplex Pattern Recognition, Classification, and Big Data Analysis
Mohammad Jamshidi - Fatemeh Daneshfar
PeQa: a Massive Persian Quenstion-Answering and Chatbot Dataset
Fatemeh Zahra Arshia - Mohammad Ali Keyvanrad - Saeedeh Sadat Sadidpour - Sayyid Mohammad Reza Mohammadi
Area-Efficient VLSI Implementation of Bit-Serial Multiplier Using Polynomial Basis over GF(2m)
Saeideh Nabipour - Javad Javidan - Gholamreza Zare Fatin
Explainable Error Detection Method for Structured Data using HoloDetect framework
Abolfazl Mohajeri Khorasani - Sahar Ghassabi - Behshid Behkamal - Mostafa Milani
An Effective Connectomics Approach for Diagnosing ADHD using Eyes-open Resting-state MEG
Nastaran Hamedi - Ali Khadem - Sajjad Vardast - Mehdi Delrobaei - Abbas Babajani-Feremi
more
Samin Hamayesh - Version 41.7.6