کنفرانس مهندسی برق ایران

صفحه اصلی / سی و سومین کنفرانس بین المللی مهندسی برق

Improving Artificial Neural Network Performance Using Hybrid Activation Function

نویسندگان :

Morteza Taheri¹ Sajad Haghzad Klidbary²

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

A Robust Video Steganography using 3D-CNN and Maximum Mean Discrepancy Cost Function

Ali Ghofrani - Rahil Mahdian Toroghi - Hassan Zareian

Design of a 2MW Medium Voltage Conventional Hybrid DC Circuit Breaker for Railway Application

Seyed Hamid Khalkhali - Mohsen Taghizadeh Kejani - Ali Asghar Razi Kazemi

Design of a High-Efficiency Balanced Power Amplifier with 68% Fractional Bandwidth

Fatemeh Mohabati - Marzieh Chegini - Mahmoud Kamarei

Effective Rate Analysis of MISO Wireless Communication Systems over EGK Fading Channels

ّfereshteh Salimian Rizi - Abolfazl Falahati

A Dual-Band LPDA Antenna Based on MXene for High-Band 5G Application

Javad Shokri seyyedi - Reza Sarraf Shirazi - Gholamreza Moradi

‌ حسگر ضریب شکست مبتنی بر فانو رزونانس در موج‌برهای فلز- عایق- فلز، با رزوناتور صفحه‌ای تزویج شده از جانب

تورج هاشمی - نسرین عبدالهی برازجان - عباس علی قنبری

امکان‌سنجی اقتصادی استقرار شبکه‌های مخابرات صنعتی در شرکت توزیع نیروی برق شهرستان مشهد (با تاکید بر نقش هوشمندسازی شبکه و بکارگیری انرژی‌های سبز)

مهدی فیل سرائی - مهدی اسماعیلی پور - علیرضا باوندپور

Giant Optical Nonreciprocity with Magnetized Epsilon-Near-Zero Materials

Zahra Chamani - Abolghasem Zeidaabadi Nezhad - Mahyar Dehdast - Zaker Hossein Firouzeh

Stochastic model predictive control based on online learning for a class of nonlinear constrained systems

Mahdi Mansoury - Mohammad Ali Badamchizadeh - Hamed Kharrati

Identification of autism spectrum disorder based on combined analysis of structural and functional connectivity

Samane Pirmoradian - Farzaneh Shayegh - Jalal Zahabi

بیشتر

ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 42.8.0