Papers by perambur neelakanta
International Conference on Neural Information Processing, 1994
Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 1988
Coordinated muscle contractions are responsible for many complex actions in biology such as respi... more Coordinated muscle contractions are responsible for many complex actions in biology such as respiration, swallowing, etc. Detailed information concerning the central nervous system (CNS) regulation may be contained in the electromyographic (EMG) signals produced by the muscles. Therefore, techniques to extract the information and produce appropriate models are desirable. In this study, multichannel EMG signal comparison by the linear prediction method is proposed. Estimation of the dissimilarities between the predicted signals can be quantified in terms of the poles of the linearly predicted signal. The method allows differentiation of the signals under various physiological as well as pathological conditions.<<ETX>>
Transactions on Machine Learning and Artificial Intelligence, Sep 3, 2022
In the contexts of deep learning (DL) considered in artificial intelligence (AI) efforts, relevan... more In the contexts of deep learning (DL) considered in artificial intelligence (AI) efforts, relevant machine learning (ML) algorithms adopted refer to using a class of deep artificial neural network (ANN) that supports a learning process exercised with an enormous set of input data (labeled and/or unlabeled) so to predict at the output details on accurate features of labeled data present in the input data set. In the present study, a deep ANN is proposed thereof conceived with certain novel considerations: The proposed deep architecture consists of a large number of consequently placed structures of paired-layers. Each layer hosts identical number of neuronal units for computation and the neuronal units are massively interconnected across the entire network. Further, each paired-layer is independently subjected to unsupervised learning (USL). Hence, commencing from the input layer-pair, the excitatory (input) data supplied flows across the interconnected neurons of paired layers, terminating eventually at the final pair of layers, where the output is recovered. That is, the converged neuronal states at any given pair is iteratively passed on to the next pair and so on. The USL suite involves collectively gathering the details of neural information across a pair of the layers constituting the network. This summed data is then limited with a specific choice of a squashing (sigmoidal) function; and, the resulting scaled value is used to adjust the coefficients of interconnection weights seeking a convergence criterion. The associated learning rate on weight adjustment is uniquely designed to facilitate fast learning towards convergence. The unique aspects of deep learning proposed here refer to: (i) Deducing the learning coefficient with a compatible algorithm so as to realize a fast convergence; and, (ii) the adopted sigmoidal function in the USL loop conforms to the heuristics of the so-called Langevin-Neelakanta machine. The paper describes the proposed deep ANN architecture with necessary details on structural considerations, sigmoidal selection, prescribing required learning rate and operational (training and predictive phase) routines. Results are furnished to demonstrate the performance efficacy of the test ANN.
Iete Journal of Research, Jul 1, 1991
A class of composite materials constituted by a mixture of two different substances (binary phase... more A class of composite materials constituted by a mixture of two different substances (binary phases) exhibit unique dielectric characteristics. In this paper, the general consideration of dielectric theory are reviewed and the state- of-the-art formulations vis-a-vis chaotic mixtures are addressed.
CRC Press eBooks, Sep 26, 1997
Strategic planning for energy and the environment, 1998
The competitive restructuring of the electric power industry is intensifying pressures for electr... more The competitive restructuring of the electric power industry is intensifying pressures for electric utilities to control costs through improved utilization of existing assets and by minimizing capital investment in new generation, transmission, and distribution capacity. This article introduces a new planning approach that can provide more informed business decisions, resulting in higher asset utilization, lower overall costs, and enhanced customer service. Unlike traditional planning methods, which assumed captive customer load growth, this process starts at the customer, focusing on how the customer`s energy service needs can best be met. Experience garnered from utilities on four continents illustrates the potential of this new approach to reduce capital expenditure for energy resource additions, often at less than one-half the cost of conventional solutions. By reorienting how utilities think, plan, and are internally organized, this new approach can assist utilities in making the fundamental transition to a customer-driven industry. Additional benefits include accurate costing of energy resources and wheeling, reduced vulnerability to conflicts over facility siting, reduced risk in a time of rapid industry change. The process proposed here may not be the best IRP process for utilities in the future but could be of significant benefit during the restructuring period.
CRC Press eBooks, Feb 6, 2018
Introduction Neural and Brain Complex Concepts of Mathematical Neurobiology Pseudo-Thermodynamics... more Introduction Neural and Brain Complex Concepts of Mathematical Neurobiology Pseudo-Thermodynamics of Neural Activity The Physics of Neural Activity: A Statistical Mechanics Perspective Stochastic Dynamics of the Neural Complex Neural Field Theory: Quasiparticle Dynamics and Wave Mechanics Analogies of Neural Networks Informatic Aspects of Neurocybernetics Appendices: Magnetism and the Ising Spin-Glass Model Matrix Methods in Little's Model Overlap of Replicas and Replica Symmetry Bibliography Index
Research Journal of Nanoscience and Nanotechnology, 2011
CRC Press eBooks, Sep 23, 2020
Information-Theoretic Aspects of Neural Networks cohesively explores this burgeoning discipline. ... more Information-Theoretic Aspects of Neural Networks cohesively explores this burgeoning discipline. Information-Theoretic Aspects of Neural Networks acts as an exceptional resource for engineers, scientists, and computer scientists working in the field of artificial ...
Uploads
Papers by perambur neelakanta