0% Complete
صفحه اصلی
/
سی و سومین کنفرانس بین المللی مهندسی برق
Wake-Sleep Learning in R-STDP-Based Spiking Neural Networks to Avoid Catastrophic Forgetting
نویسندگان :
Mehrdad Baradaran
1
Katayoon Kobraei
2
Saeed Reza Kheradpisheh
3
1- دانشگاه شهید بهشتی تهران
2- دانشگاه شهید بهشتی تهران
3- دانشگاه شهید بهشتی تهران
کلمات کلیدی :
Neuroscience-inspired AI،Spiking Neural Networks (SNNs)،Continual Learning،Catastrophic Forgetting،Generative Replay
چکیده :
Incremental Learning (IL) enables systems to learn new tasks over time without forgetting previous knowledge, a challenge known as catastrophic forgetting. This is especially prominent in Class-Incremental Learning (CIL), where models must sequentially learn new classes without task identity information. To address this problem, we propose a two-phase generative replay mechanism inspired by biological memory consolidation processes. During the "Day Phase," the model learns new tasks using reward-modulated Spike-Timing-Dependent Plasticity (R-STDP), while the "Night Phase" reinforces memory by generating and replaying synthetic data that simulates previously learned tasks. We evaluate our approach on Spiking Neural Networks (SNNs), leveraging their biologically inspired dynamics and energy-efficient architecture. Experiments were conducted on MNIST and Fashion-MNIST (FMNIST) datasets across three approaches: generative replay, original data replay, and a hybrid method combining both strategies. Experimental results demonstrate up to a 24% improvement in accuracy for CIL tasks on the MNIST dataset using the generative replay method, compared to standard SNNs without the Night Phase, highlighting the role of the Night Phase in enhancing performance. This work emphasizes the capability of SNNs to integrate biological principles into AI, bridging the gap between artificial intelligence and neuroscience.
لیست مقالات
لیست مقالات بایگانی شده
بهبود تخصیص منابع لبهها در شبکه LTE مبتنی بر محاسبات لبه با رویکرد تعادل میان تاخیر و قابلیت اطمینان
ایمان عظیمی احمدآبادی - علی اکبر تدین تفت
Power exchanging of a VPP with its neighboring VPPs and participating in Day-ahead and spinning reserve markets
Mohammad Fazel Dehghanniri - Masoud Ali Akbar Golkar - Farzin Ghasemi
A Novel Multi-Variable Search Space Method for Selective Harmonic Control-PWM in Active Power Filters
Mohammadhossein Mohammadpour - Faegheh Taghipour Reyneh - Hoda Ghoreishy - Seyyed Asghar Gholamian
Accurate Methods for Automatic Detection of Characteristic Points in Electrocardiograms
Seyedeh Mersedeh Bagheri - Mohammad Pooyan
بخشبندی خودکار تصاویر تشدید مغناطیسی ستون فقرات کمری با شبکه سِگیونِت
محمد انصاری فرد - رضا آقایی زاده ظروفی
Single-Frequency Microwave Measuring System for Liquid Characterization for Point-of-Care Testing
Saeed Javadizadeh - Mohammadjavad Bouloorchi Tabalvandani - Majid Badieirostami - Mahmoud Shahabadi
Medial Residual Encoder Layers for Classification of Brain Tumors in Magnetic Resonance Images
Zahra Sobhaninia - Nader Karimi - Pejman Khadivi - Shadrokh Samavi
بهینه سازی تزویج فیبر نوری باریک شده و موجبر نوری بر بستر پلیمر
مهتاب حسینعلی زاده - مونا ثریا - غلام محمد پارسا نسب - شکراله کریمیان
Battery Sizing for energy management of islanded Microgrid considering the impact of discharge duration on Lead-Acid Battery effective capacity
Mehrdad Bagheri Sanjareh - Mohammad Hassan Nazari - Narges Sadat Ghiasi - Seyyed Mohammad Sadegh Ghiasi - Seyed Hoseein Hosseinian
Resilient Control of Mixed Traffic Systems Under Denial-of-Service Attacks
Ehsan Foroughi Asl - Mohammad Haeri
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 42.8.0