کنفرانس مهندسی برق ایران

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 Baradaran¹ Katayoon Kobraei² Saeed Reza Kheradpisheh³

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

Evaluating the Impact of Operation Scheduling Methods on Microgrid Reliability Using Monte Carlo Simulation

Mahsa Omri - Mohammad Jooshaki - Ali Abbaspour - Mahmud Fotuhi-Firuzabad

Modeling of seawater desalination by reverse osmosis method powered by wind turbine

Bahareh Iranmanesh - Gholam Hossein Riahy Dehkordi

ارائه یک مبدل DC-DC منبع امپدانسی تک سوئیچه تک هسته مغناطیسی فوق افزاینده مناسب برای استفاده در کاربرد های انرژی نو

معصومه پرستش - سجاد رستمی

A Novel Approach to Cheating Prevention in Demand Side Management Algorithms

Farahnaz Haftbaradaran - Ali Akhtari - Massoud Reza Hashemi - Zahra Baharlouei

Design of Dual-beam Orthogonal Circular Polarized Leaky-wave Holographic Antenna

Mohammad Amin Chaychizadeh - Nader Komjani

Impact of Sierpinski fractal shape on the performance of ultrathin-film silicon solar cells

Mohammad Ali Shameli - Sayyed Reza Mirnaziry - Leila Yousefi

Design and fabrication of a microstrip phase shifter based on liquid crystal

Sadegh Rajabi Doulataabadi - Seyed Hossein Hosseini Biuki - Farid Khoshkhati - Seyed Abbas Jazayeri Moghadas - Mohammad Masoudi Mohammadi - Mehdi Ahmadi-Boroujeni

Intrusion Detection System for Securing Agriculture 4.0 against DDoS Attacks using Deep Learning and Machine Learning Models

Mohammad Mirmarghabi - Ahmad Afshar - Hajar Atriyanfar

Network-based functional connectivity in MDD with suicide ideation before and after TMS: An fMRI case study

Moslem Khafi - Morteza Fattahi - Hamid Soltanian-Zadeh - Reza Rostami

امکان‌سنجی اقتصادی استقرار شبکه‌های مخابرات صنعتی در شرکت توزیع نیروی برق شهرستان مشهد (با تاکید بر نقش هوشمندسازی شبکه و بکارگیری انرژی‌های سبز)

مهدی فیل سرائی - مهدی اسماعیلی پور - علیرضا باوندپور

بیشتر