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
Autonomous Guidance and Control of Satellite Formation Flying Based on Q-Learning with Collision Avoidance Capability
Hamid Mohsennezhad - Mohammadrasoul Kankashvar - Hossein Bolandi
Effect of Passivation on the Structural and Electronic Properties of Armchair MoSe2 Nanoribbons: A First-Principles Investigation
ََAmirreza Ghazi - Arash Yazdanpanah
ارائه مبدل DC-DC غیر ایزوله هیبریدی بهره ولتاژ بالا با سوئیچ فعال سلفی
حسن زارعین - مجتبی حیدری - سیدمحمد دهقان دهنوی
A Framework for Plant Topology Extraction Using Process Mining and Alarm Data
Amir Neshastegaran - Ali Norouzifar - ایمان ایزدی
Entanglement-Assisted Classical-Quantum Multiple Access Wiretap Channel: One-shot Achievable Rate Region
Hadi Aghaee - Bahareh Akhbari
کاهش نویز و کلاتر در تصاویر رنگی داپلر اولترسوند
بهینا علیزاده - سید محمود سخایی
Design and Simulation of Nano-Second Pulsed Power Generator for Cancer Treatment and Considering Load Effect
Reza PirNia - Maryam A.Hejazi - Nasrin Deldadeh
طراحی سازه ی الکترودی بهینه جهت انجام آزمایشات امپدانس متری سلولی و غیر سلولی
علی منفردی - نسرین هاشمی - مهرداد ساویز
Design and Determing Two Separate Rotor Axial Flux Permanent Magnet Motor Load and Efficinecy
Siamak Omrani - Ahmad Darabi
Field Effect Phototransistor Based on Thin Film Ag2S Nanocrystals
Hossein Roshan - Mohammad Hossein Sheikhi
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 41.7.4