0% Complete
فارسی
Home
/
چهاردهمین کنفرانس بین المللی فناوری اطلاعات و دانش
Improving Training Stability in Variational Autoencoders Through the Integration of Score Matching Loss
Authors :
Amirreza Mokhtari Rad
1
Pouya Ardehkhani
2
Hormehr Alborzi
3
1- پردیس فارابی دانشگاه تهران
2- پردیس فارابی دانشگاه تهران
3- پردیس فارابی دانشگاه تهران
Keywords :
Variational Auto Encoder،Training،Stability،Generative Models،Score Matching
Abstract :
In this research, a Variational Autoencoder (VAE) model was developed, and the CIFAR100 dataset was employed as the primary data source. The problem addressed pertained to the instability in the training process of VAE models. To mitigate this issue, various loss expressions were explored, including the use of score matching loss independently, in conjunction with total variation loss, and in combination with reconstruction loss. The innovative approach revealed that when score matching loss was integrated either with total variation loss or when applied as a standalone loss function, the training process exhibited increased stability. This was evident through smoother loss curves and latent space visualizations that displayed characteristics akin to a normal distribution. As a consequence, this novel approach promises the potential for building more stable generative models, which can significantly enhance the overall training process in VAEs. This innovation provides a valuable contribution to the field of generative modeling, with the prospect of addressing the longstanding challenge of training stability in VAEs, thereby opening avenues for more efficient and effective model development and application.
Papers List
List of archived papers
Violence detection using one-dimensional convolutional networks
Narges Honarjoo - Ali Abdari - Dr Azadeh Mansouri
بهبود تشخیص نفوذ به شبکه اینترنت اشیاء با استفاده از مدل ترکیبی الگوریتم های بهینهسازی ازدحام ذرات، گرگ خاکستری و جنگل تصادفی
مهدی علیرضانژاد - عمار عبیس حسین المعموری
AI-based Message Spam Classification Framework for Secure Autonomous Vehicles Communication
Riya Upadhyay - Mili Virani - Lakshit Pathak - Rajesh Gupta - Sudeep Tanwar - Hossein Shahinzadeh
Human Resource Allocation to the Credit Requirement Process, A Process Mining Approach
Omid Mahdi Ebadati - Mohammad Mehrabioun - Shokoofeh Sadat Hosseini
جمعآوری، تحلیل و خلاصه سازی نظرات کاربران فارسی زبان در شبکههای اجتماعی پیرامون بیماری فراگیر کووید-19
محمدرضا شمس - محمد یاسین فخار محمدرضا شمس - محمد یاسین فخار -
StockFM: پیش بینی قیمت بازار بورس ایران به کمک مدل بنیادین سری زمانی
فاطمه چیت ساز - سامان هراتی زاده
Information Technology Risk Management Model for Remote Control Vehicles
Hamid Reza Naji - Aref Ayati
پیش بینی گره های رهبر در شبکه های اجتماعی با استفاده از پیش بینی پیوند
روح اله رشیدی - فرساد زمانی بروجنی - محمد رضا سلطان آقایی - هادی فرهادی
Face Recognition Based on Local Statistical Features and Artificial Neural Network
Mehdi Moghimi - Dr Hadi Grailu
A Data-Efficient Approach to Solar Panel Micro-Crack Detection via Self-Supervised Learning
Alireza Akhavan safaei - Pegah Saboori - Reza Ramezani - Morteza Tavana
more
Samin Hamayesh - Version 41.3.1