لطفا منتظر بمانید ...
0% Complete
صفحه اصلی
/
سی و سومین کنفرانس بین المللی مهندسی برق
Improved Generative Adversarial Network with Differentiable KS Distance
نویسندگان :
Siavash Sadeghi Ivrigh
1
Mohammadreza Hassannejad Bibalan
2
Asghar Keshtkar
3
1- دانشگاه بین‌المللی امام خمینی (ره)
2- دانشگاه بین‌المللی امام خمینی (ره)
3- دانشگاه بین‌المللی امام خمینی (ره)
کلمات کلیدی :
GANs،KS distance،Sigmoid activation function،Deep learning،Machine learning
چکیده :
Generative adversarial networks (GANs) have emerged as a powerful framework for generating realistic data. However, evaluating the quality of generated samples remains a challenging task. This paper introduces a novel metric for evaluating GANs based on the Kolmogorov-Smirnov (KS) distance. The KS distance is a robust statistical measure to assess the similarity between two probability distributions. To efficiently compute the KS distance, we propose a novel approach that leverages the sigmoid activation function in the final layer of the discriminator. By carefully tuning the weights of this layer, we can approximate the KS distance between the real and generated data distributions. This approach offers a more efficient and effective way to evaluate GAN performance, leading to improved training and better-quality generated samples.
لیست مقالات
لیست مقالات بایگانی شده
Study of the interaction between different parameters in the fabrication of paper-based microfluidic devices using the wax printing method
MOHAMMAD DERAKHSHANI - SEYED HOSSEIN TAYEBI - MEHRDAD LOTFI CHOOBBARI - AMIR JAHANSHAHI
Performance Analysis of an UAV-assisted cognitive D2D communication-based Disaster Response Network
Hossein Mohammadi Firozjae - Javad Zeraatkar Moghaddam - Mehrdad Ardebilipour
Image steganography Based on Chaos permutation, authentication and wiener deconvolution
Ali Sheidaee - Mohammad Asadpour - Leili Farzinvash
Placement and sizing of electric vehicle charging stations in distribution network with stochastic generation
Pooya Tadayonroody - Maryam Ramezani - Mohsen Akafimobarake - Hamid Falaghi - Mozhde Farhangroody
A New Model of Interleaved Boost CF-CLLC Integrated Resonant Converter with Fixed-Frequency PWM Control for Renewable Energy Applications in Fuel Cell and Battery-Powered Electric Vehicles
Mina Taheri - Hossein Askariyan Abyane
GAN-Driven Image Generation for Metamaterial Absorbers Using Mean and Variance Encoding
Atefe Shahsavaripour - Mohammad Hossein Badiei - Leila Yousefi - Ahmad Kalhor
CNN-LSTM model for Confusion Classification; using Single-Channel EEG
Amirhossein Aran - Zahra Ghanbari - Mohammad Hassan Moradi
شناسایی کمپلکس های پروتئینی با رویکرد خوشه بندی EM و با استفاده از داده های زیستی
مریم مولی وردیخانی - سعید جلیلی
کنترل بازوی ربات دو درجه آزادی با کنترل‌کننده مود لغزشی مرتبه کسری فازی-تطبیقی پایانه‌ای
مائده نفیسی فر - متین جزءاسلامی - ابوالفضل جلیلوند - سمیرا نریمان پور - فرهاد بیات
A Data-Driven Two-Layer MPC with Safety Filter for Range-of-Motion-Constrained Tracking in a Knee Rehabilitation Exoskeleton
Ashkan Jelodar - Mohammad Olyai - Khalil Alipour - Bahram Tarvirdizadeh - Majid Sorouri - Mohammad Ghamari
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 44.7.2
