Entity

Time filter

Source Type

Gurgaon, India

Sharma S.K.,Indraprastha University | Chandra P.,University of Delhi
Proceedings - 2010 International Conference on Computational Intelligence and Communication Networks, CICN 2010 | Year: 2010

This paper presents an adaptive slope basic dynamic node creation algorithm for single hidden layer neural networks (ASBDNCA). The proposed algorithm is a constructive approach of building a single hidden layer neural network. The ASBDNCA puts emphasis on architectural adaptation and functional adaptation during learning. It uses gradient descent optimization method in sequential mode as the weights update rule of individual hidden node. To achieve functional adaptation, the slope of the sigmoidal activation function (SAF) is adapted during learning. The algorithm determines not only optimal number of hidden nodes, as also optimum value of the slope parameter for the non-linear nodes. One simple variant derived from ASBDNCA in which the slope parameter of SAF is fixed. Both the variants are compared to each other on five function approximation tasks. Simulation results reveal that adaptive slope SAF present several advantages over traditional fixed shape sigmoidal activation function, resulting in increased flexibility, smoother learning, better convergence and better generalization performance. © 2010 IEEE. Source


Suri B.,Indraprastha University | Jatana N.,MSIT | Tomer M.,MSIT
Proceedings of the 2015 IEEE 3rd International Conference on MOOCs, Innovation and Technology in Education, MITE 2015 | Year: 2015

Learning Software Engineering principles, processes, methods and tools is a prerequisite to becoming a Software Engineer. The technological advancements and revolution in this new century are probing the boundaries of education and training in software engineering. This work tries to locate the shortcomings in existing approaches to Education in Software Engineering (ESE) in respect to today's technological advancements. We hereby proposed a new model for Education in Software Engineering to bridge the industry-academia gap. © 2015 IEEE. Source


Pandey D.,University of Petroleum and Energy Studies | Singh A.K.,Indraprastha University | Sarkar A.,University of Petroleum and Energy Studies
76th European Association of Geoscientists and Engineers Conference and Exhibition 2014: Experience the Energy - Incorporating SPE EUROPEC 2014 | Year: 2014

The transportation of heavy oil is always the matter of concern for oil industries. The viscosity of heavy oil ranges from 200 CP (centipoise) to 5,000 CP and is strict function of composition of hydrocarbons. Due to high viscosity, the mobility of heavy crude is very low at reservoir conditions. Moreover, it is very difficult to flow heavy crude at cold temperatures from offshore regions to the refinery. Therefore, despite in the improvements in thermal recovery methods such as Toe to Heel Air Injection (THAI), Steam assisted Gravity Drainage (SAGD), Steam Injections, etc., some diluents like C4+ and hydrocarbon gases are introduced with it. Recently, the team of researchers under Rongjia Tao, a physicist at Temple University in Philadelphia, has found an alternative way to transport heavy crude by applying electric and magnetic impulses. Magnetic impulses are basically more effective for paraffin based crude oil and its effect lasts for 8 to 10 hours after the implementation of strong magnetic field. This technical paper aims at analyzing Mr. Tao's experiment, rectifying its limitations and proposing a better experimental setup for the pilot experiment so that it can be further extrapolated to the industrial point of application. Source


Sharma S.K.,Indraprastha University | Chandra P.,University of Delhi
Advanced Materials Research | Year: 2012

In this paper we propose a constructive algorithm with adaptive sigmoidal function for designing single hidden layer feedforward neural network (CAASF). The proposed algorithm emphasizes on architectural adaptation and functional adaptation during training. This algorithm is a constructive approach to building single hidden layer neural networks dynamically. The activation functions used at non-linear hidden nodes are belonging to the well-defined sigmoidal class and adapted during training. The algorithm determines not only optimum number of hidden nodes, as also optimum sigmoidal function for the non-linear nodes. One simple variant derived from CAASF is where the sigmoidal function used at the hidden nodes is fixed. Both the variants are compared to each other on five regression functions. Simulation results reveal that adaptive sigmoidal function presents several advantages over traditional fixed sigmoid function, resulting in increased flexibility, smoother learning, better convergence and better generalization performance. © (2012) Trans Tech Publications, Switzerland. Source


Sharma S.K.,Indraprastha University | Chandra P.,University of Delhi
Advanced Materials Research | Year: 2012

This paper presents cascading neural networks using adaptive sigmoidal function (CNNASF). The proposed algorithm emphasizes on architectural adaptation and functional adaptation during training. This algorithm is a constructive approach to building cascading architecture dynamically. The activation functions used at the hidden layers' node are belonging to the well-defined sigmoidal class and adapted during training. The algorithm determines not only optimum number of hidden layers' node, as also optimum sigmoidal function for them. One simple variant derived from CNNASF is where the sigmoid function used at the hidden layers' node is fixed. Both the variants are compared to each other on five regression functions. Simulation results reveal that adaptive sigmoidal function presents several advantages over traditional fixed sigmoid function, resulting in increased flexibility, smoother learning, better convergence and better generalization performance. © (2012) Trans Tech Publications, Switzerland. Source

Discover hidden collaborations