0% Complete
صفحه اصلی
/
سی و سومین کنفرانس بین المللی مهندسی برق
Improving Artificial Neural Network Performance Using Hybrid Activation Function
نویسندگان :
Morteza Taheri
1
Sajad Haghzad Klidbary
2
1- زنجان
2- زنجان
کلمات کلیدی :
Activation Function, Hybrid Activation Function, Neural Networks, Deep Learning.،Hybrid Activation Function،Cifar and Mnist Dataset.
چکیده :
Abstract— Choosing the optimal activation function for the training of deep neural networks has always posed a significant challenge due to its substantial impact on the network performance and training speed. Despite the impressive performance demonstrated by various nonlinear non-monotonic activation functions, such as rectified linear units, hyperbolic tangent, sigmoid, swish, mish, Smish, and Logish, only a restricted subset of these functions is commonly embraced in most applications, primarily because of inherent inconsistencies or other limitations. This research introduces a new hybrid activation functions designed to surpass other activation functions. The results from our experiments suggest that the new activation function(AF) we introduced performs well across diverse datasets. Also, These findings indicate that the activation function we developed are better suited for intricate deep-learning models. In comparison to Sigmoid, Relu and other AFs, our proposed activation function has increased accuracy on MNIST, Cifar10, Cifar100 dataset. Significantly, our purposed AF has the maximum accuracy (100%) compared to other well-known activation functions on MNIST dataset.
لیست مقالات
لیست مقالات بایگانی شده
Novel Wideband Dual-Polarized Base-Station Antenna
Farzad Alizadeh - Changiz Ghobadi - Javad Nourinia - Keyhan Hosseini - Bahman Mohammadi
A Technical-Managerial Framework for Determining Periodic Performance Indices and Operating Ranges of Power Grid Frequency
Hamed Delkhosh - Hossein Seifi - Sajjad Gholamnejad - Morteza Yousefian
A High Dynamic Range Differential Rectifier for RF Energy Harvesting
Ataollah Mahsafar - Mohammad Yavari
Social Welfare Maximization with Demand Response Program Using Stackelberg Game Theory
Mahtab Seyyedi - Ebrahim Pirmoradi - Turaj Amraee
Analysis of the RCS of Luneburg Reflector in Bistatic Mode
Mohammad Amin Abdollahi - Gholamreza Moradi
Fabrication, Simulation and Modeling of a T-Shaped Coaxial Stub Resonator
Abolfazl Ebrahimpour - Sepehr Sahab - Javad Shokri Seyyedi - Younes Sahranavard - Gholamreza Moradi
An Investigation on Transfer Learning for Classification of COVID-19 Chest X-Ray Images with Pre-trained Convolutional-based Architecture
Mobina Abdoli Nemati - ََAmirreza Baba Ahmadi
مدلسازی ترانسفورماتورهای کم تلفات در شرایط عملکرد غیرعادی و بررسی تأثیر آن ها بر تلفات فنی شبکه قدرت
محمدرضا موسوی خادمی - غلامرضا زارع پلکوئی - مرتضی موسوی خادمی
Machine Learning Approach for Retrieval of Complex Permittivity in Cavity Resonators
Kianoosh Kazemi - Gholamreza Moradi
Modeling of Photo-thermoelectric Current Effects in Phase Change Material based Optical Nano Dipole Antenna Energy Transducer
Daniyal Khosh Maram - Seyed Asad Amirhosseini
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 40.4.2