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
A Hybrid Chaos-Assisted Key Derivation Framework for Secure IoT Data Encryption Using AES-256-GCM
Reza Sedagheh Maskan Sadigh - Shadi Janbabaei - Peyman Ayubi
Low-Cost Clock Distribution Network in Highly Compact Integrated Circuits Against Single Event Transients
Ehsan Borhani nia - Amir Mohammad Hoseini
Design and Simulation of a MEMS Capacitive Switch With Low Pull-in Voltage and High Switching Speed
Davoud Razaghpoor - Mir Majid Ghasemi - Saeid Afrang - Amir Fathi - Asma Akbarli
Modeling the Cable Bridge Based on Two Dimensional System and Analysing the Stability of Desired Model Based on Wave Advanced Model
Mehdi Mirshahi - Masoud Shafiee - Mehdi Mohammadi
Robust Model Predictive Control of Cyber-Physical Linear Parameter Varying System subject to deception attacks and bounded disturbances
Sepideh Jahani VakilKandi - Farhad Bayat - Abolfazl Jalilvand
A Multi-Branch Deep Learning Architecture with Hierarchical Fusion for Real-Time Short-Term Multi-Horizon PV Energy Forecasting
Sepehr Shakibi - Melika Vafaee Taj Khatooni - Mohsen Hamzeh
Extreme Modulation Index Using Time Periodic Epsilon-Near-Zero Materials
Atefeh Erfaniazad - Mohammad Memarian
Effect of the Number of Quantum-Dot Layers on the Performance of the 1.3 µm InAs/GaAs VCSELs
Sara Alaei - Mahmood Seifouri - Saeed Olyaee - Gholamreza Babaabbasi
Optimized 5G-MMW Compact Yagi-Uda Antenna Based on Machine Learning Methodology
Alireza Jafarieh - Mahdi Nouri - Hamid Behroozi
MoMed: An Affordable Mechanical Ventilator
Mahdi Robati - Ali Sadighi - Mohammad Ali Nazari - Hamid Naseri
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 44.7.2