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
طراحی آنتن سرآتش پهن باند مبتنی بر پلاسمون پلاریتونهای سطحی جعلی
فرشاد ارغنده - بیژن عباسی آرند - مریم حصاری شرمه
High Performance and Low Power Spintronic Binarized Neural Network Hardware Accelerator
Milad Tanavardi Nasab - Arefe Amirany - Mohammad Hossein Moaiyeri - Kian Jafari
طراحی مدولاتور الکتروجذبی پلاسمونیک مبتنی بر Vo2 باساختار اسلت برای بهبود عملکرد در طول موج 1550 نانومتر مخابراتی
حبیبه صمدی - حمید واحد - هادی صوفی
A Novel Analytical Tuning Method for Designing of Composite Nonlinear Feedback Control Law in Continuous-time Dynamical Systems
Ali Vazani - Valiollah Ghaffari
Study of the interaction between different parameters in the fabrication of paper-based microfluidic devices using the wax printing method
MOHAMMAD DERAKHSHANI - SEYED HOSSEIN TAYEBI - MEHRDAD LOTFI CHOOBBARI - AMIR JAHANSHAHI
Robust H∞ Control Design for Variable-Speed Wind Turbines Using Bilinear Matrix Inequalities
Hamidreza Javanmardi - Alireza Hamedi - Mahya Rahimzadeh
طراحی کنترلکنندهی جدولبندی بهرهی پسخورد خروجی کلیدزن مقاوم برای سیستمهای پارامتر متغیر خطی نامعین چندوجهی پیوسته-زمان
رضا یاوری - سعید شمقدری - آرش صادقزاده
Design and Implementation of a Compact 4×4 Microstrip Patch Antenna Array with Circular Polarization for Nano Satellite Applications
Mohammad Ghasemi - Majid Afsahi - Shoresh Namdari
Energy-Efficient Residue-to-Binary Conversion Based on a Modulo-Adder-Free Architecture
Kamalaldin Mozaffari Maid - Amir Sabbagh Molahosseini
Sparsity Domain Smoothing Based Thresholding Recovery Method for OFDM Sparse Channel Estimation
Mohammad Hossein Bahonar - Reza Ghaderi Zefreh - Rouhollah Amiri
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 42.8.0