لطفا منتظر بمانید ...
0% Complete
صفحه اصلی
/
سی و چهارمین کنفرانس بین المللی مهندسی برق
Guided Training of Spiking Neural Networks via an Auxiliary Artificial Neural Network
نویسندگان :
Neda Falah
1
Majid Shalchian
2
1- دانشگاه صنعتی امیرکبیر(پلی تکنیک تهران)
2- دانشگاه صنعتی امیرکبیر(پلی تکنیک تهران)
کلمات کلیدی :
Spiking Neural Networks (SNNs)،Artificial Neural Networks (ANNs)،Guided Learning،Hybrid Training،MNIST Classification
چکیده :
Spiking Neural Networks (SNNs) offer brain-inspired, energy-efficient computation, but their training is hindered by non-differentiable spike signals. This paper introduces a novel hybrid framework where an auxiliary Artificial Neural Network (ANN) guides weight updates for an SNN. The ANN observes the SNN’s internal states—such as membrane potentials and spike activities—and predicts gradient-like updates, enabling stable and efficient optimization. Experiments on MNIST demonstrate that the proposed SNN+ANN model achieves 97.7% accuracy, surpassing the 92% accuracy of a baseline SNN, while also converging faster and with greater stability. The method effectively combines the temporal efficiency of spiking computation with the robust optimization of differentiable networks, offering a promising direction for neuromorphic learning systems.
لیست مقالات
لیست مقالات بایگانی شده
Deep SqueezeNet Based Technique for Detection of High Impedance Arcing Faults in Electric Power Distribution Networks
Amin Mohammadi - Mohsen Jannati - Mohammadreza Shams
Interval-Based Setting Approach for Distance Relays Considering Uncertainties Using Monte Carlo Simulation
Abolfazl Hadadi - Mohammad Javad Jalilian - Behrooz Vahidi - Gholam Hossein Riahy Dehkordi
Photo-Thermoelectric Energy Conversion in Phase-Change Optical Nanoantennas: A Modeling Study
Daniyal Khoshmaram - Milad Jahangiri - Seyed Asad Amirhosseini
Crypto Currency Price Prediction Using Preprocessed Scaled Inputs LSTM Model Enhanced by Improved Gray Wolf Optimization
Amir RabbaniParsa - Mahboobeh Hoshmand - Seyyed Abed Hosseini
بررسی یک روش معکوس برای استخراج ثابت دی الکتریک محلی با استفاده از میکروسکوپ نوری روبشی میدان نزدیک
علی اقراری - محمد نشاط
Rail-to-Rail Time-Domain Comparator with Ultra-Low Power Consumption by Reducing Static Current and Short-Circuit Current
Sadegh Bagheri - Hossein Yaghoobzadeh Shadmehri - Amirali Hosseini
Radio frequency energy harvesting with multi band rectenna in GSM 1800, UMTS2100 and WiFi
Sahar Bayat - Zahra Bahrami - Asghar Keshtkar
ZnO-based Acoustofluidics: Droplet-based Particle Manipulation
Sara Abbasi - Behdad Barahimi - Sara Darbari - Mohammad Kazem Moravvej-Farshi - Mohammad Zabetian
An IoT-Based System for Water Consumption Optimization and Reliability Enhancement
M. J. Bagherzadeh - S. Sayardoost
A Boost and Luo Based Non-isolated DC-DC Converter Suitable for DC Link of High Voltage Applications
Ali Meftahpour - Hesam Ehsan - Hossein Gholizadeh - Mohammad Hamed Samimi
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 44.7.2
