0% Complete
صفحه اصلی
/
سی و سومین کنفرانس بین المللی مهندسی برق
Classifier Fusion Based on Extracted Features Using a Spiking Neural Network from Handwritten Digits
نویسندگان :
Ali Gholamzade Fard Kazzazi
1
Malihe Nazari
2
Fariba Bahrami
3
1- دانشگاه صنعتی امیرکبیر
2- دانشگاه تهران
3- دانشگاه تهران
کلمات کلیدی :
spiking neural network،spike timing dependent plasticity،unsupervised learning،feature extraction،classification،classical classifiers،classifier fusion
چکیده :
The third generation of neural networks, known as spiking neural networks (SNNs), are capable of solving all problems that traditional networks can solve, and computationally, they can perform even more powerfully. Spiking neurons are closer to biological reality. For these reasons, these networks have gained significant attention in recent years. When using these networks for tasks such as pattern recognition or classification, there is no precise method for data classification. In previous works that employed spiking neural networks for classification, each approach generally utilized the unsupervised learning mechanisms that existed in these networks to classify the data through different techniques. Due to the weaknesses in the classification layer of spiking neural networks, we turned to the use of the firing rates of spiking neurons to extract features, which were then passed to classical classifiers. When we used spiking neurons for classification, we achieved an accuracy of 80.17%, and when we added a classical classifier in the third layer of the network, the accuracy increased to 84.48%. Based on the results obtained, the use of a classical classifier layer improved the network's accuracy. Additionally, it increased the execution speed compared to the case where a spiking neuron layer was used in the classification layer, and it reduced the need for extensive hyperparameter tuning of the SNN. Finally, we applied the Decision Template method for classifier fusion, which led to an accuracy of 84.87%. The results show that using classifier fusion methods improves the performance of the network.
لیست مقالات
لیست مقالات بایگانی شده
A Low Phase Noise and High Frequency DLL-Based Clock Multiplier with Enhanced Locking Range
Alireza Toloue Khorasanian - Saeed Saeedi
A Brief Review on DC-Link Control Strategies in Microgrids
Mehran Seydi - Hassan Moradi CheshmehBeigi - Mohammad Hossein Mousavi
SAR Images Clustering Based on Modified Nonlinear Orthogonal non-Negative Matrix Factorization (NMF)
Mahdi Jowkar dehouei - Soolmaz Khazandi - Yaser Norouzi
Manifold Learning-Assisted Physical Layer Key Generation for LoRaWAN: an Experimental Study
Hossein Aghajari - Hamed Bakhtiari babadegani, - Mehdi Naderi soorki - Sajad Ahmadinabi - Seyed mohsen Ahmadi
Scalable Multipurpose Smart Indoor Lighting System for Wireless Sensor Networks
Atefesadat Seyedolhosseini - Reza Nemati - Hossein Maghsoumi - Shokrollah Karimian - Nasser Masoumi
Holographic Principle Inspired Metal-Only Spoof Surface Plasmon Polariton Leaky-wave Antenna with Circular Polarization
Sajjad Zohrevand - Mohammad Amin Chaychi zadeh - Nader Komjani
Differentiating Brain Connectivity Networks in ADHD and Normal Children using EEG
Roqaie Moqadam - Nazila Loghmani - Alireza Khorrami Moghaddam - Armin Allahverdy
Optimized ANFIS-based Control Design Using Genetic Algorithm to Obtain the Vaccination and Isolation Rates for the COVID-19
Zohreh Abbasi - Mohsen Shafieirad - Amir Hossein Amiri Mehra - Iman Zamani
برنامه ریزی احتمالاتی بهینه فیلترهای پسیو در حضور خودروهای برقی متصل به شبکه با قابلیت جبرانسازی هارمونیک در شبکههای توزیع
پریسا انجم شعاع - سعید اسماعیلی
A New Model of Interleaved Boost CF-CLLC Integrated Resonant Converter with Fixed-Frequency PWM Control for Renewable Energy Applications in Fuel Cell and Battery-Powered Electric Vehicles
Mina Taheri - Hossein Askariyan Abyane
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 42.5.3