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
Finite-time consensus of multi-agent systems via event-triggered control
Mehdi Zamanian - Farzaneh Abdollahi - Seyyed Kamaleddin Yadavar Nikravesh
Sum-Rate Maximization for NOMA-Based Networks with D2D Communications using Matching Theory
َAlireza Gholamrezaee - Hamid Farrokhi - Javad Zeraatkar Moqaddam
Improving the Performance and Robustness of Non-Minimum Phase Systems Using Integrated Feedforward-IMC Technique
Saeedreza Tofighi
Optimal Receiver Placement in Distributed Passive Sensor Networks: A DRL Approach
Hossein Nikaein - Mohammad Reza Jabbari - Maedeh Kadkhodaie Elyaderani - Saeed Gazor
Reduction of Common-Mode Voltage in Cascaded H-Bridge Inverter Under Faulty Conditions
Ashkan Raki - Yousef Neyshabouri - Hossein Iman-Eini - Mahdi Aslanian
Radio frequency energy harvesting with multi band rectenna in GSM 1800, UMTS2100 and WiFi
Sahar Bayat - Zahra Bahrami - Asghar Keshtkar
Integrated strategy for segment BRATS using co-operation of FCM and TL under abnormal behavior of noises
Arman Zafaranchi - Pedram Salehpoor
Lateral Stability of Electric Vehicles in Car-Following Scenario Using High-Accuracy NMPC
Mohammad Behzad Roohi - Mohammad Javad Yazdanpanah
A New Unsupervised Feature Learning Method for Object Recognition using Prior-Knowledge Data
Ashkan Farrokhi - Hadi Seyedarabi
An Improved Real-Time Implementation of Adaptive Neuro-fuzzy Controller
Iman Gholizadeh - Haniye Raziyan - Reza Javidan
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 40.4.2