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
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
Ultra-Low-Latency QCA Adder Design Using an Innovative Carry Generator
Mohammad Mahdi Cheraghi - Reza Omidi - Ali Azarpeyvand
Recurrence Quantification and Machine Learning: A Novel Approach for Parkinson’s Disease Diagnosis from EEG Signals
Asghar Zarei - Alireza Talesh Jafadideh
Reduction of Common-Mode Voltage in Cascaded H-Bridge Inverter Under Faulty Conditions
Ashkan Raki - Yousef Neyshabouri - Hossein Iman-Eini - Mahdi Aslanian
Structural Stability and Electron Density Analysis of Doped Antimonene: A First-Principles Study
Arash Yazdanpanah Goharrizi - Peyman Saberi Parsa
An Analysis of Nash Equilibrium Learning through Myopic Decision-making in Incomplete Information Double Sided Auction Games within Markets
Hesam Farzaneh - Parsa Zholideh
Evaluating the effect of electric vehicle charging station locations on line flows:An analytical approach
Mohammad Hasan Nikkhah - Mahdi Samadi
Adaptive Attitude Synchronization and Tracking Control of Spacecraft Formation Flying using Reaction Wheel without Angular Velocity Measurement
Amin Mihankhah - Ali Doustmohammadi
حسگر غیرتهاجمی تشخیص قندخون با استفاده از تکنیک مایکروویو بر مبنای تشدید فرکانسی
نازنین افشاری - سید محمد هاشمی - فاطمه گران قراخیلی
Non-homogeneous interference suppression in OFDM array radars using direct data domain approach
Sima Shariatmadari
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 42.0.4