Please wait ...
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
A Real-Time and Robust Approach for Banknote Recognition
Hani Abdi - Mohammad Javad Parseh
Recommendation Systems in Smart Agriculture: Pathway to a well-designed system
Ahmad Nameni - Amir Ghafarian Daneshmand - Omid Mahdi Ebadati E
ارائه تکنیک یادگیری چندهسته ای مبتنی بر روش بهینه سازی برای مسئله دسته بندی سیگنال های EEG مبتنی بر تصور حرکتی
یوکابد امیری - حسام عمرانپور
طراحی واسط کاربری مبتنی بر رفتار و احساسات کاربران در سیستم های هوشمند
فاطمه صبائی - دکتر احمد عبداله زاده بارفروش
پیش بینی بیماری قلبی با استفاده از روش تحلیل شبکه ای
هدیه مشتاقی محمدزاده - فاطمه باقری
Dealing with Black-hole Attacks in Inter-vehicle Networks Using the Packet Delivery Rate Algorithm
Marzieh Sedighi - Mehdi Hamidkhani - Mostafa Sadeghi
Design of low-latency Floating-Point units for Softmax Computation in Transformer-based Large Language Models
Hoda Ghabeli - Amir Sabbagh Molahosseini
An approach to model the optimal service provisioning in vehicular cloud networks
Farhoud Jafari Kaleibar - Maghsoud Abbaspour
نظرکاوی در سطح مفهوم با استفاده از رویکردی ترکیبی
سیدرضا قادریان خیرآبادی سیدرضا قادریان خیرآبادی -
Knowledge Extraction from Technical Reports Based on Large Language Models: An Exploratory Study
Parsa Bakhtiari - Hassan Bashiri - Alireza Khalilipour - Masoud Nasiripour - Moharram Challenger
more
Samin Hamayesh - Version 45.0.1