International Conference on Computer and Knowledge Engineering

Home / 11th International Conference on Computer and Knowledge Engineering

PowerLinear Activation Functions with application to the first layer of CNNs

Authors :

Kamyar Nasiri¹ Kamaledin Ghiasi-Shirazi²

1- Computer Engineering Dept. Ferdowsi University of Mashhad Mashhad, Iran 2- Computer Engineering Dept. Ferdowsi University of Mashhad Mashhad, Iran

Keywords :

PowerLinear activation function, Activation function, Kernel methods, Generalized convolution operators, CNNs

Abstract :

Convolutional neural networks (CNNs) have become the state-of-the-art tool for dealing with unsolved problems in computer vision and image processing. Since the convolution operator is a linear operator, several generalizations have been proposed to improve the performance of CNNs. One way to increase the capability of the convolution operator is by applying activation functions on the inner product operator. In this paper, we will introduce PowerLinear activation functions, which are based on the polynomial kernel generalization of the convolution operator. EvenPowLin functions are the main branch of the PowerLinear activation functions. This class of activation functions is saturated neither in the positive input region nor in the negative one. Also, the negative inputs are activated with the same magnitude as the positive inputs. These features made the EvenPowLin activation functions able to be utilized in the first layer of CNN architectures and learn complex features of input images. Additionally, EvenPowLin activation functions are used in CNN models to classify the inversion of grayscale images as accurately as the original grayscale images, which is significantly better than commonly used activation functions.

Papers List

List of archived papers

DPRNN-FORMER: AN EFFICIENT WAY TO DEAL WITH BLIND SOURCE SEPARATION

Ramin Ghorbani - Sajad Haghzad Klidbary

An Effective Connectomics Approach for Diagnosing ADHD using Eyes-open Resting-state MEG

Nastaran Hamedi - Ali Khadem - Sajjad Vardast - Mehdi Delrobaei - Abbas Babajani-Feremi

FAHP-OF: A New Method for Load Balancing in RPL-based Internet of Things (IoT)

Mohammad Koosha - Behnam Farzaneh - Emad Alizadeh - Shahin Farzaneh

Enhancing Lighter Neural Network Performance with Layer-wise Knowledge Distillation and Selective Pixel Attention

Siavash Zaravashan - Sajjad Torabi - Hesam Zaravashan

FedBrain-Distill: Communication-Efficient Federated Brain Tumor Classification Using Ensemble Knowledge Distillation on Non-IID Data

Rasoul Jafari Gohari - Laya Aliahmadipour - Ezat Valipour

TriFuse-PdM: High-Fidelity Machine Failure Prediction Using Hybrid Resampling and Model Calibration

Saghar Shafaati - Javad Mohammadzadeh

Real-time Implementation of Fuzzy Visual Servoing for a Delta Robot via Shape and Color Detection

Nooshin Najafian - Alireza Ashrafi Majd - Abbas Ansaroudi - Sahar Aghazadeh - Manizheh Zakeri - Mohammad-Reza Sayyed Noorani

Using Deep Learning for Classification of Lung Cancer on CT Images in Ardabil Province

Mohammad Ali Javadzadeh Barzaki - Jafar Abdollahi - Mohammad Negaresh - Maryam Salimi - Hadi Zolfeghari - Mohsen Mohammadi - Asma Salmani - Rona Jannati - Firouz Amani

Analyzing the Impact of COVID-19 on Economy from the Perspective of User’s Reviews

Fatemeh Salmani - Hamed Vahdat-Nejad - Hamideh Hajiabadi

Community-Based QoE Enhancement for User-Generated Content Live Streaming

Reza Saeedinia - S.Omid Fatemi - Daniele Lorenzi - Farzad Tashtarian - Christian Timmerer