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
Compact Multiband HMSIW Antenna Loaded with Complementary Split Ring Resonators
Rasol Zayer - Mohamamd Naghi Azarmanesh - Javad Nourinia - Changiz Ghobadi - Farzad Alizadeh - Bahman Mohammadi
Design and Simulation of Long Slot SIW Leaky Wave Antenna for Automotive Radar Application
Jamal Kazazi - Alireza Rahmani - Mahmoud Kamarei
Deception Attack Detection and Resilient Control in Platoon of Smart Vehicles
Hassan Mokari - Elnaz Firouzmand - Iman Sharifi - Ali Doustmohammadi
Wideband Multi-hole Coupler Using Ridge Gap Waveguide Technology
Ahmad Bakhtafrouz - Zahra Akhoondmahdi - Mohammad Matin Mashayekhi
بررسی و تحلیل تقابل تلفات و پروفیل ولتاژ به کمک الگوریتم ژنتیک چند هدفه در سیستم های قدرت در حضور سیستم های انتقال قدرت انعطاف پذیر
سجاد احمدنیا - حبیب رجبی مشهدی
Manifold Learning-Assisted Physical Layer Key Generation for LoRaWAN: an Experimental Study
Hossein Aghajari - Hamed Bakhtiari babadegani, - Mehdi Naderi soorki - Sajad Ahmadinabi - Seyed mohsen Ahmadi
روشی نوین مبتنی بر سیمپلکسهای متوالی برای غلبه بر چالشهای حل پخش بار بهینه
فاطمه زاده محمدی - حسین شریف زاده
Design and implementation of a light box to measure the dimensions of objects
Mohammad Imani - Amir Mousavinia - Behruz Nasihatkon
A Highly-Linear Wideband Differential Low-Noise Amplifier Using Derivative Superposition Technique
Abolfazl Rajaiyan - Mehdi Saberi
Detecting Variance Changes in Alarm Systems Using Generalized Delay-timers
Zahra Sharifi - Iman Izadi - Jafar Ghaisari
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 42.0.4