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
Spatio-Temporal Graph Neural Networks for Accurate Crime Prediction
Rojan Roshankar - Mohammad Reza Keyvanpour
WBT-GAN:Wavelet based Generative Adversarial Network for Texture Synthesis
Sara Saberi moghadam - Reza Azmi - Maral Zarvani
Developing Convolutional Neural Networks using a Novel Lamarckian Co-Evolutionary Algorithm
Zaniar Sharifi - Khabat Soltanian - Ali Amiri
Area-Efficient VLSI Implementation of Bit-Serial Multiplier Using Polynomial Basis over GF(2m)
Saeideh Nabipour - Javad Javidan - Gholamreza Zare Fatin
No-Reference Video Quality Assessment by Deep Feature Maps Relations
Amir Hossein Bakhtiari - Azadeh Mansouri
An Automated Visual Defect Segmentation for Flat Steel Surface Using Deep Neural Networks
Dorna Nourbakhsh Sabet - Mohammad Reza Zarifi - Javad Khoramdel - Yasamin Borhani - Esmaeil Najafi
Efficient Object Detection using Deep Reinforcement Learning and Capsule Networks
Sobhan Siamak - Eghbal Mansoori
Facial Emotion Recognition Under Mask Coverage Using a Data Augmentation Technique
Aref Farhadipour - Pouya Taghipour
Dynamic Hand Gesture Recognition with 2DCNN-LSTM and Improved Keyframe Extraction
Narjes Heidari - Javid Norouzi - Mohammad Sadegh Helfroush - Habibollah Danyal
Weakly Supervised Convolutional Neural Network for Automatic Gleason Grading of Prostate Cancer
Maryam Kamareh - Mohammad Sadegh Helfroush - Kamran Kazemi
more
Samin Hamayesh - Version 41.5.3