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
Sparse Beamforming Design for Non-Coherent UD-CRAN with mm-Wave Fronthaul Links
Alireza M. Hosseini - Dr Abbas Mohammadi
Predictive Maintenance using LSTM and Adaptive Windowing
Aien Ghanbari Adivi - Behrouz Shahgholi Ghahfarokhi
Artificial Empathy in AI-Based Mental Health: A Review
Shabnam Moradi
Distributed coordination protocol for event data exchange in IoT monitoring applications
Behnam Khazael - Hadi Tabatabaee Malazi
تحلیل احساسات نظرات کاربران تجارت الکترونیک با استفاده از تکنیک های یادگیری عمیق
محیا دشتیانه - رضا قاسمی یقین
ML-based Optical Fibre Fault Detection in Smart Surveillance and Traffic Systems
Rushil Patel - Sana Narmawala - Nikunjkumar Mahida - Rajesh Gupta - Sudeep Tanwar - Hossein Shahinzadeh
PersianRAG A Retrieval Augmented Generation System for Persian Language
Hossein Hosseini - Mohammad Sobhan Zare - Amir Hossein Mohammadi - Arefeh Kazemi - Zahra Zojaji - Mohammad Ali Nematbakhsh
An Efficient Link Prediction Method using Community Structures
Dr Hadi Shakibian - Setareh Mokhtari
A Real-Time and Robust Approach for Banknote Recognition
Hani Abdi - Mohammad Javad Parseh
Design and modeling of a waiter robot
Amin Mohammadnejad - Hami Tourajizadeh
more
Samin Hamayesh - Version 42.5.2