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
Smart EV Charging in Residential Power Grids Considering Users’ Preferences
Mahya Shahshahani - Ali Moradi Amani - Mahdi Jalili
Performance improvement of automated parking by considering road incline and wheel slippage
Ali Anisi - Moosa Ayati - Yassin Riyazi - Ali Asadian
A High Gain, High IIP3, Perfect Input Matching, Programmable Gain LNA in CMOS Technology
Amirhossein Tajik - Seyedali Samareh Taherinasab - Samad Sheikhaei
Optimization and Analysis of Transformer Hot Spot Temperature Under Harmonic Conditions with Different Windings
Mehran Nemati - Hamed Karimi - Alireza Siadatan - Maryam Sepehrinour
A 5kW Bidirectional Isolated On-Board EV Battery Charger Using Hybrid PFC/Inverter
Amir Hossein Dabbagh - Hamed Arvani - Ebrahim Afjei
Decentralized Optimization in Scheduling Virtual Power Plant (VPP)
Amir Hossein Gholami - Amir Abolfazl Suratgar - Mohammad Bagher Menhaj - Mohammad Reza Hesamzadeh
Development of a Tilt Bicopter: Experimental Results
Ali Moaveni - Alireza Bahmanyar - Arshia Rezaei - Amin Talaeizadeh - Aria Alasti
Second-order Sliding Mode Control for DC-DC buck converter with input Voltage Ripple Elimination
Maede Azimi - Mehdi Asadi - Adel Zakipour
Noninvasive Diagnosis of the Type of Breast Tumor through Artificial Neural Networks
Pooya Tahmasebi - Maryam Mehdizadeh Dastjerdi - Ali Fallah - Saeid Rashidi
Human detection and following by a mobile robot using YOLO structured convolutional neural network
Yasan Majidi - Amir Hossein Hassanabadi
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 40.4.2