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
Multiphysics Analysis of HTS Transformer utilizing Stainless Steel Stabilizer on Short Circuit Condition
Ashkan Mirzaei Rajeooni - Hossein Heydari - Mohammad Khakroei - Mahdi Rahimi Pirbasti
Development of Iterative Learning Control Method Based on Markov Parameters for High-Order Discrete-Time Singular Systems
Meysam Azhdari - Tahereh Binazadeh - Ali Gholami
Robust Wireless Power Transfer by Self-Oscillating Controlled Inverter and Double-D Pads
Alireza Eikani - Mohammad Amirkhani - Hossein Jafari - Hesamodin Abdoli - Sadegh Vaez-Zadeh - Ghasem Rezazadeh
FPGA-Based Multiplier with a New Approximate Full Adder for Error-Resilient Applications
Ali Ranjbar - Elham Esmaeili - Shabnam Rafiei - Nabiollah Shiri
Transfer learning using deep convolutional neural network for predicting dementia severity
Vahid Asayesh - Mehdi Dehghani - Majid Torabi Nikjeh - Sepideh Akhtari khosrowshahi
تشخیص و مکان یابی خطاها در آرایه های فتوولتائیک متصل به شبکه
سعید انصاری - حیدر صامت - تیمور قنبری
Binomial Distribution based K-means for Graph Partitioning Approach in Partially Reconfigurable Computing system
Zahra Asgari - Maryam Sadat Mastoori
Uneven Illumination Correction in Whole Slide Imaging using Pix2Pix
Sama Nemati - Hasti Shabani
Design, Simulation and Analysis of a MIM Plasmonic Sensor Based on the Cross-Shaped Resonator
Setare Farzane - Hassan Kaatuzian - Leila Hajshahvaladi
Φ-OTDR Event Classification Using Machine Learning and Optical Signal Processing
Amir Babaoughli - Tohid Alizadeh - Seyed Sadra Kashef
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 42.5.3