Please wait ...
0% Complete
Home
/
11th International Conference on Computer and Knowledge Engineering
PowerLinear Activation Functions with application to the first layer of CNNs
Authors :
Kamyar Nasiri
1
Kamaledin Ghiasi-Shirazi
2
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
Online Task Offloading and Scheduling in Fog-Cloud Environment based on Reinforcement Learning
Ali Sheidaee - Leili Farzinvash - Alireza Sokhandan
Farsi Text in Scene: A new dataset
Ali Salmasi - Ehsanollah Kabir
Adaptive Sliding Window Optimization for Multi-Dimensional Data Streams Using Reinforcement Learning
Abolfazl Zarghani
Enhancing Cloud Security with Federated CNN-LSTM: A Novel Approach to Intrusion Detection
Reyhaneh Ilaghi - Raheleh Ilaghi - Fereshteh Rahmani - Seyyed hamid Ghafoori
A Robust Network for Embedded Traffic Sign Recognation.
Omid Nejati Manzari - Shahriar Baradaran Shokouhi
A Language-Independent Approach to Classification of Textual File Fragments: Case Study of Persian, English, and Chinese Languages
Fatemeh Mansouri Hanis - Hamidreza Khoshvaghti - Mehdi Teimouri - Hadi Veisi
DEW-WIN: A Dynamic Energy-aware Window-based Scheduler for Mixed-criticality Systems
Mahin Moradiyan - Yasser Sedaghat - Pouria Hosseini - Yousef Rezazadeh
Lempel-Ziv-based Hyper-Heuristic Solution for Longest Common Subsequence Problem
Mahdi Nasrollahi - Reza Shami Tanha - Mohsen Hooshmand
Collaborative LLM Reasoning for Vulnerability Detection in Smart Contracts
Amirreza Samari - Parsa Hedayatnia - Seyyed Javad Bozorgzadeh Razavi - Mohammad Allahbakhsh - Haleh Amintoosi
Pruning and Mixed Precision Techniques for Accelerating Neural Network
Mahsa Zahedi - Mohammad Sediq Abazari Bozhgani - Abdorreza Savadi
more
Samin Hamayesh - Version 46.0.2