Proceedings Article10.1109/IJCNN.2011.6033508
A Fast Learning Complex-valued Neural Classifier for real-valued classification problems
R. Savitha,Sundaram Suresh,Narasimhan Sundararajan +2 more
- 01 Jul 2011
- pp 2243-2249
24
TL;DR: Performance comparison with existing complex-valued and real-valued classifiers show the superior classification performance of the FLCNC.
read more
Abstract: This paper presents a fast learning fully complex-valued classifier to solve real-valued classification problems, called the ‘Fast Learning Complex-valued Neural Classifier’ (FLCNC). The FLCNC is a single hidden layer network with a non-linear, real to complex transformed input layer, a hidden layer with a fully complex activation function and a linear output layer. The neurons in the input layer convert the real-valued input features to the Complex domain using an unique non-linear transformation. At the hidden layer, the complex-valued transformed input features are mapped onto a higher dimensional Complex plane using a fully complex-valued activation function of the type of ‘sech’. The parameters of the input and hidden neurons of the FLCNC are chosen randomly and the output parameters are estimated analytically which makes the FLCNC to perform fast classification. Moreover, the unique nonlinear input transformation and the orthogonal decision boundaries of the complex-valued neural network help the FLCNC to perform accurate classification. Performance of the FLCNC is demonstrated using a set of multi-category and binary real valued classification problems with both balanced and unbalanced data sets from the UCI machine learning repository. Performance comparison with existing complex-valued and real-valued classifiers show the superior classification performance of the FLCNC.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
2012 Special Issue: A meta-cognitive learning algorithm for a Fully Complex-valued Relaxation Network
TL;DR: Performance studies on a function approximation and real-valued classification problems show that proposed McFCRN performs better than the existing results reported in the literature.
65
Regularized Weighted Circular Complex-Valued Extreme Learning Machine for Imbalanced Learning
Sanyam Shukla,Ram Narayan Yadav +1 more
TL;DR: A regularized weighted ELM (RWCC-ELM) is proposed, which incorporates the strength of both CC- ELM and WELM and outperforms CC-ELm and W ELM for most of the evaluated data sets.
31
Fast Learning Fully Complex-Valued Classifiers for Real-Valued Classification Problems
R. Savitha,Sundaram Suresh,Narasimhan Sundararajan,Hyeongeu Kim +3 more
- 29 May 2011
TL;DR: Two fast learning neural network classifiers with a single hidden layer using the phase encoded transformation and the bilinear transformation with a branch-cut at 2p as the activation functions in the input layer to map the real-valued features to the complex domain.
30
A Cognitive Ensemble of Extreme Learning Machines for Steganalysis Based on Risk-Sensitive Hinge Loss Function
TL;DR: A risk-sensitive hinge loss function-based cognitive ensemble of extreme learning machine (ELM) classifiers for JPEG steganalysis and performance results show the superior classification ability of the cognitive ensemble ELM classifier.
28
Complex-valued neuro-fuzzy inference system for wind prediction
K. Subramanian,R. Savitha,Sundaram Suresh +2 more
- 10 Jun 2012
TL;DR: The proposed CNFIS is a four layered network which realizes zero-order Takagi-Sugeno-Kang based fuzzy inference mechanism and its gradient descent based learning algorithm developed employing Wirtinger calculus.
23
References
•Book
Neural Networks: A Comprehensive Foundation
Simon Haykin
- 16 Jul 1998
TL;DR: Thorough, well-organized, and completely up to date, this book examines all the important aspects of this emerging technology, including the learning process, back-propagation learning, radial-basis function networks, self-organizing systems, modular networks, temporal processing and neurodynamics, and VLSI implementation of neural networks.
•Book
An Introduction to Support Vector Machines
Nello Cristianini,John Shawe-Taylor +1 more
- 01 Mar 2000
TL;DR: This book is the first comprehensive introduction to Support Vector Machines, a new generation learning system based on recent advances in statistical learning theory, and introduces Bayesian analysis of learning and relates SVMs to Gaussian Processes and other kernel based learning methods.
Introduction to Support Vector Machines
Dustin Boswell
- 01 Jan 2002
TL;DR: Support Vector Machines (SVM’s) are intuitive, theoretically wellfounded, and have shown to be practically successful.
2.2K
A Fast and Accurate Online Sequential Learning Algorithm for Feedforward Networks
TL;DR: The results show that the OS-ELM is faster than the other sequential algorithms and produces better generalization performance on benchmark problems drawn from the regression, classification and time series prediction areas.
2K