A Generalization Method of Partitioned Activation Function for Complex Number

نویسندگان

  • HyeonSeok Lee
  • Hyo Seon Park
چکیده

A method to convert real number partitioned activation function into complex number one is provided. The method has 4em variations; 1 has potential to get holomorphic activation, 2 has potential to conserve complex angle, and the last 1 guarantees interaction between real and imaginary parts. The method has been applied to LReLU and SELU as examples. The complex number activation function is an building block of complex number ANN, which has potential to properly deal with complex number problems. But the complex activation is not well established yet. Therefore, we propose a way to extend the partitioned real activation to complex number.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Optimal Portfolio Selection for Tehran Stock Exchange Using Conditional, Partitioned and Worst-case Value at Risk Measures

This paper presents an optimal portfolio selection approach based on value at risk (VaR), conditional value at risk (CVaR), worst-case value at risk (WVaR) and partitioned value at risk (PVaR) measures as well as calculating these risk measures. Mathematical solution methods for solving these optimization problems are inadequate and very complex for a portfolio with high number of assets. For t...

متن کامل

Sesterin as a biomolecule

Sestrins (Sesns), highly conserved stress-inducing metabolic proteins, are known to protect organisms against various harmful stimuli including DNA damage, oxidative stress, endoplasmic reticulum (ER) stress, and hypoxia. Sestrins regulate metabolism mainly through activation of AMP-dependent protein kinase (AMPK) and inhibition of rapamycin complex 1 (mTORC1). Sestrins also play a pivotal role...

متن کامل

Multiple Complex Extreme Learning Machine using Holomorphic Mapping for Prediction of Wind Power Generation System

In this paper, a wind prediction system for the wind power generation using ensemble of multiple complex extreme learning machines (C-ELM) is proposed. The extreme learning machines is a single layer feed forward neural network having a fast learning and better generalization ability than the gradient-based learning methods. C-ELM is chosen as base classifier because it is very suitable for pro...

متن کامل

The Kinetic and Thermal Degradation Studies of N-(4-Acetyl-phenyl)-acetimidic Acid Pyridine-3-yl ester Metal(II) Complexes

Schiff base complexes of transition metals are of particular interest to inorganic chemists because of their structural, spectral and chemical properties, which are often strongly dependant on the nature of the ligand structure. Large number of metal (II) complexes with Schiff-base ligands has been extensively studied for their interesting structural specialties, applications and properties. Th...

متن کامل

Locally Estimated Hemodynamic Response Function and Activation Detection Sensitivity in Heroin-Cue Reactivity Study

Introduction: A fixed hemodynamic response function (HRF) is commonly used for functional magnetic resonance imaging (fMRI) analysis. However, HRF may vary from region to region and subject to subject. We investigated the effect of locally estimated HRF (in functionally homogenous parcels) on activation detection sensitivity in a heroin cue reactivity study. Methods: We proposed...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:
  • CoRR

دوره abs/1802.02987  شماره 

صفحات  -

تاریخ انتشار 2018