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

رمزنگاری نوین صدا با استفاده از نظریه آشوب و عملگرهای ژنتیک در سامانه‌های VOIP

علی خرمی - جعفر شرفخانی

A Wideband White and Colored Noise Generator as an Environmental Communication Systems Controller

Somayeh Mehraban - Nasser Masoumi

Design and fabrication tip tapered fiber optic dopamine sensor based on LSPR

Roksana Esmaeilpour - Mohammad Ismail zibaii - Masoumeh Barkand - Marzieh Pajouhandeh - Soroush Rostami - Mehdi Banihashemi - Mohammad-Mahdi Babakhani-fard

Design and fabrication of wearable and stretchable EEG headband using textile-based electrode wire

Kourosh Motiepor - Arman Modoudi Yaghouti - Simin Bakhtiyari - Amir Jahanshahi - Roohollah Bagherzadeh

Learning-Based Routing Policy For Wireless Sensor Networks

‪Najim Halloum‬‏ - Yousef Darmani - Ali Ahmadi

Improving CCA-based methods for SSVEP classification using a common source graph

Nastaran Noori - Sepideh Hajipour Sardouie

Design Investigation of a Broadband Polarization Rotator Using SIW Technology with T-Shaped Slots

Amin Azimi - Mohammad.H Neshati

Study of an Improved Flux Reversal Permanent Magnet Outer-Rotor Motor

Mohammad Reza Sarshar - Mohammad Amin Jalali Kondelaji - Mojtaba Mirsalim

شبیه سازی رفتار و عملکرد مقره پلیمری 20 کیلوولت با اعمال آلودگی سطحی از نقطه نظر ارزیابی و سنجش جریان خزشی و ارائه الگوی معادل سازی آن

سیدمحمدعلی طباطبائی - حمید جوادی - مسعود عبدالحسین پور - فرامرز قلیچی

Surface roughness classification in dynamic touch using EEG signals

Ali Amini - Karim Faez - Mahmood Amiri

بیشتر

ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 42.0.4