25,904 Hits in 4.3 sec

Optimized Functional Link Artificial Neural Network for Multi-label Classification

Anwesha Law, Balasubramanyam Evani, Ashish Ghosh
2019 Australian Journal of Intelligent Information Processing Systems  
To handle the inherent complexity of multi-label data, a compact and efficient network known as functional link artificial neural network (FLANN) has been explored.  ...  Analysis of the results have generated some interesting conclusions and optimal models for multi-label classification.  ...  Conclusion This paper develops six models (five novel and one existing) of functional link artificial neural network for multi-label classification.  ... 
dblp:journals/ajiips/LawEG19 fatcat:rbevwtf53jbaxcnklghh2bm32m

A Survey: Hybrid Intelligent Modeling Technique for Data Classification

Tanu Rani, Mr. Narender Kumar
2017 IJARCCE  
The artificial neural network is the widely used technique for classification and prediction.  ...  Optimization techniques and hybridization improve ANN performance. GA is an optimization technique that produces optimization of the problem by using natural evolution.  ...  Elisseeff and Weston [33] proposed an SVM Ranking algorithm for multi-label classification that minimizes the ranking loss. V.  ... 
doi:10.17148/ijarcce.2017.65119 fatcat:isxth7kxfrey5arah7zkrlcnr4

Integration of Autoencoder and Functional Link Artificial Neural Network for Multi-label Classification [article]

Anwesha Law, Ashish Ghosh
2021 arXiv   pre-print
A novel neural network model has been developed where the input features are subjected to two transformations adapted from multi-label functional link artificial neural network and autoencoders.  ...  Multi-label (ML) classification is an actively researched topic currently, which deals with convoluted and overlapping boundaries that arise due to several labels being active for a particular data instance  ...  Autoencoder integrated multi-label functional link artificial neural network In this article, a two-layer transformation based neural network has been proposed for multi-label classification which incorporates  ... 
arXiv:2107.09904v1 fatcat:f7abp7jixfcyrgntakomxbq2ua

Functional Link Artificial Neural Network for Classification Task in Data Mining

B.B. Misra, S. Dehuri
2007 Journal of Computer Science  
In this study, we have used Functional Link Artificial Neural Networks (FLANN) for the task of classification.  ...  In solving classification task of data mining, the traditional algorithm such as multi-layer perceptron takes longer time to optimize the weight vectors.  ...  Hence, to resolve few of the issues, in this study we use functional link artificial neural network for solving the classification problem. Pao et al.  ... 
doi:10.3844/jcssp.2007.948.955 fatcat:t46tc54exbajjektjmu5huw6pa

Metric learning with relational data

Jiajun Pan, Hoel Le Capitaine
2019 The European Symposium on Artificial Neural Networks  
Experiments and comparisons of the two settings for a collective classification task on real-world datasets show that our method i) presents a better performance than other approaches in both settings,  ...  The objective of this paper is to propose metric learning algorithms that consider multi-relational data.  ...  For instance, social service networks, Wikipedia network, molecular biology classification and so forth.  ... 
dblp:conf/esann/PanC19a fatcat:ja3bypzvgzedxihfrh32ovhjh4

Multi-Task Network Representation Learning

Yu Xie, Peixuan Jin, Maoguo Gong, Chen Zhang, Bin Yu
2020 Frontiers in Neuroscience  
By optimizing the multi-task loss function, our framework jointly learns task-oriented embedding representations for each node.  ...  The original network and the incomplete network share a unified embedding layer followed by node classification and link prediction tasks that simultaneously perform on the embedding vectors.  ...  ACKNOWLEDGMENTS We would like to thank Yu Zhang and Yiming Fan for thoughtful comments on the manuscript and language revision. We were grateful to all study participants for their time and effort.  ... 
doi:10.3389/fnins.2020.00001 pmid:32038151 pmcid:PMC6989613 fatcat:xeuo264qsne73aiddfdne6xm6y

Multi-view ANNs for Multi-relational Classification

Hongyu Guo, H.L. Viktor
2006 The 2006 IEEE International Joint Conference on Neural Network Proceedings  
Artificial neural networks (ANNs) provide a general, effective and practical approach for learning complex target functions.  ...  This paper introduces a new approach, the multiple view artificial neural networks (MVNNs) method, to address the need for bridging the gap between ANNs and relational databases.  ...  INTRODUCTION Artificial neural networks (ANNs) provide a general, effective and practical approach for learning complex target functions.  ... 
doi:10.1109/ijcnn.2006.247280 dblp:conf/ijcnn/GuoV06 fatcat:bmh7yaoabrfafp3a2t275kaxxm

Learning from partially labeled data

Siamak Mehrkanoon, Xiaolin Huang, Johan A. K. Suykens
2020 The European Symposium on Artificial Neural Networks  
There are several possibilities for designing such models ranging from shallow to deep models.  ...  In particular, in this context one can refer to semi-supervised modelling, transfer learning, domain adaptation and multi-view learning among others.  ...  Thus, learning from partially labeled data becomes attractive for training deep neural networks for those tasks. There are different ways to use unlabeled data for training neural networks.  ... 
dblp:conf/esann/MehrkanoonHS20 fatcat:hdjcnwwu4fgzbjwv5uotkcyvua

A Review of Image Classification Approaches and Techniques

2017 International Journal of Recent Trends in Engineering and Research  
This paper study about different classification techniques such as Artificial Neural Networks (ANN), Naive Bayes (NB), K-Nearest Neighbor (KNN), Multi-Layered Perceptron (MLP), Kernel Support Vector Machines  ...  Many classification techniques have been developed for image classification.  ...  Artificial Neural Networks Artificial Neural Network (ANN) is a type of artificial intelligence that limits some functions of the person mind.  ... 
doi:10.23883/ijrter.2017.3033.xts7z fatcat:xqm6swzihbdf7g4y6lvgdfoxbm

Firefly Algorithm with Artificial Neural Network for Time Series Problems

Mohammed Alweshah
2014 Research Journal of Applied Sciences Engineering and Technology  
For the purpose of solving time series classification problems used the multi-layered perceptrons Artificial Neural Networks (ANN).  ...  For this reason, several algorithms had been proposed to train the parameters of the neural network for time series classification problems.  ...  METHODOLOGY Firefly algorithm with Artificial Neural Networks (ANN): Rumelhart et al. (1986) have proposed the multi-layered perceptrons (Artificial Neural Networks) for the purpose of solving time series  ... 
doi:10.19026/rjaset.7.757 fatcat:huhxs7lqhbhbdnh634bmsfk6zy

Multinomial Classification of "Hete-Neurons" in Heterogeneous Information Networks

2020 International Journal of Advanced Trends in Computer Science and Engineering  
sigmoid function.  ...  A multi-class Classification approach is experimented with a dataset which contains 1050 queries from well reputed university exam papers and showed a higher accuracy rate with 99.86 when tested with the  ...  for multi-class classification of a Hete-Neuron shows optimal result.  ... 
doi:10.30534/ijatcse/2020/107952020 fatcat:ktnn6zo47zcr7aywemegulvwma


2020 European Journal of Technic  
In this study, deep neural networks are used for the classification of marbles which can be used in the industry.  ...  The fact that both new dataset and deep neural networks are used for the first time in marble classification are among the positive aspects of this study.  ...  These features have been tested with many artificial neural networks. Then classification was made by using hierarchical radial basis function network (HRBFN) [9] .  ... 
doi:10.36222/ejt.671527 fatcat:gteir4prubbxdmrebntrhveoki

An Insight into Extreme Learning Machines: Random Neurons, Random Features and Kernels

Guang-Bin Huang
2014 Cognitive Computation  
(2) Does there exist unified framework for feedforward neural networks and feature space methods?  ...  ., feature learning, clustering, regression and classification) be made without tuning hidden neurons (including biological neurons) even when the output shapes and function modeling of these neurons are  ...  confidence on artificial neural networks.  ... 
doi:10.1007/s12559-014-9255-2 fatcat:k66cuxdi3rervdnyfa6yqlgxlm

Data Clustering Optimization using Support Vector Machines

2019 International journal of recent technology and engineering  
For this, we present an optimization of the existing methods based on artificial neural networks, through combining two machine learning procedures; unsupervised clustering followed by a supervised classification  ...  framework as a Fast, highly scalable and precise packets classification system.  ...  The first step was to apply artificial neural network classification on clusters before and after SVM optimization.  ... 
doi:10.35940/ijrte.b2717.078219 fatcat:bkbn6uzuzbbntmg6n5xxtckouq

Employees Attrition Detection using PSONN

Yogesh Yogesh, Sudhir Shrivastav
2019 International Journal of Innovative Research in Computer Science & Technology  
Many research works uses artificial intelligence models for inventory management. One amongst the area for inventory management is worker behavior in a company.  ...  One of the suitable solutions is to design optimal inventory model. Major concern of industry is to design suitable inventory model.  ...  The artificial neural network (ANN) is used to derive optimal inventory policies.  ... 
doi:10.21276/ijircst.2019.7.5.2 fatcat:d4rzdompindznbjdpawmfga2ee
« Previous Showing results 1 — 15 out of 25,904 results