Filters








28,732 Hits in 8.9 sec

Multi-layered GMDH-type Neural Network Algorithm Using Principal Component-Regression Analysis and PSS Criterion

Tadashi Kondo, Junji Ueno, Shoichiro Takao
2013 Proceedings of the ISCIE International Symposium on Stochastic Systems Theory and its Applications  
In this study, the principal component-regression analysis is used for estimating the parameters of the neurons and stable and accurate multi-layered architectures of the GMDH-type neural networks are  ...  In this study, a hybrid Group Method of Data Handling (GMDH)-type neural network algorithm using principal component-regression analysis is proposed and applied to the nonlinear system identification.  ...  The heuristic self-organization method can be used for organizing the multi-layered architecture but the multicolinearity in the partial polynomials of the neurons is generated.  ... 
doi:10.5687/sss.2013.273 fatcat:golrddsdencmlkdyz64wmtnogi

A New Multi-layered GMDH-type Neural Network Algorithm Using Principal Component-Regression Analysis

Tadashi Kondo, Junji Ueno, Shoichiro Takao
2012 Proceedings of the ISCIE International Symposium on Stochastic Systems Theory and its Applications  
In this study, the principal component-regression analysis is used for estimating the parameters of the neurons and stable and accurate multi-layered architectures of the GMDH-type neural networks are  ...  In this study, a revised Group Method of Data Handling (GMDH)-type neural network using principal component-regression analysis is proposed and applied to the nonlinear system identification.  ...  The heuristic self-organization method can be used for organizing the multi-layered architecture but the multicolinearity in the partial polynomials of the neurons is generated.  ... 
doi:10.5687/sss.2012.83 fatcat:3qmjbrglebcnxlbdkdmrjmttha

An Abstract Domain to Infer Ordinal-Valued Ranking Functions [chapter]

Caterina Urban, Antoine Miné
2014 Lecture Notes in Computer Science  
The traditional method for proving program termination consists in inferring a ranking function.  ...  We have implemented a prototype static analyzer for a while-language by instantiating our domain using affine functions as polynomial coefficients.  ...  We are very grateful to Damien Massé for the interesting discussions and his helpful suggestions. We also thank the anonymous reviewers for their careful reviews and their useful comments.  ... 
doi:10.1007/978-3-642-54833-8_22 fatcat:hicucj3pu5ds5bvmu25b4jmasq

Feedback GMDH-type Neural Network and Its Application to Medical Image Analysis of Liver Cancer

Tadashi Kondo, Junji Ueno
2011 Proceedings of the ISCIE International Symposium on Stochastic Systems Theory and its Applications  
The identification results show that the feedback GMDH-type neural network algorithm is useful for the nonlinear system identification and the medical image analysis of liver cancer and is ideal for practical  ...  neural network, the radial basis function (RBF) type neural network and the polynomial type neural network.  ...  (3) Calculating the partial descriptions For each combination, the partial descriptions of the nonlinear system are calculated by applying the regression analysis to the training data.  ... 
doi:10.5687/sss.2011.256 fatcat:j7wdbipkyfeg5cqou3ifojtwwa

Amortized Resource Analysis with Polymorphic Recursion and Partial Big-Step Operational Semantics [chapter]

Jan Hoffmann, Martin Hofmann
2010 Lecture Notes in Computer Science  
A previous work approached the problem with an automatic type-based amortized analysis for polynomial resource bounds.  ...  The soundness of the inference is proved with respect to a novel operational semantics for partial evaluations to show that the inferred bounds hold for terminating as well as non-terminating computations  ...  Polynomial Potential Our previous work [9] showed that an automatic amortized analysis can also be used to derive polynomial resource bounds by extracting linear inequalities from a program.  ... 
doi:10.1007/978-3-642-17164-2_13 fatcat:vyz7wqlxwfbwddkr3ll2ym5hay

Medical Image Recognition of Heart Regions by Deep Multi-Layered GMDH-Type Neural Network Using Principal Component-Regression Analysis

Tadashi Kondo, Junji Ueno, Shoichiro Takao
2015 Journal of Robotics, Networking and Artificial Life (JRNAL)  
network architecture is automatically organized using the principal component-regression analysis from the medical images of the heart regions.  ...  This algorithm is applied to the medical image recognition of the heart regions and it is shown that this algorithm is useful for the medical image recognition of the heart regions because deep neural  ...  The training data are used for estimating the parameters of the partial descriptions which describe the partial relationships of the nonlinear system.  ... 
doi:10.2991/jrnal.2015.2.3.7 fatcat:75ljjpwynffnje6scafa4fl3se

Medical Image Diagnosis of Liver Cancer by Multi-layered GMDH-type Neural Network Using Principal Component-Regression Analysis and PSS Criterion

Tadashi Kondo, Junji Ueno, Shoichiro Takao
2013 Proceedings of the ISCIE International Symposium on Stochastic Systems Theory and its Applications  
The recognition results are compared with the conventional sigmoid function neural network trained using back propagation method and it is shown that this algorithm is useful for CAD of liver cancer.  ...  In this study, hybrid multi-layered GMDH-type neural network using principal component-regression analysis is proposed.  ...  Training data is used for estimating parameters of partial descriptions which describe partial relationships of the nonlinear system.  ... 
doi:10.5687/sss.2013.255 fatcat:k4nw62hsf5hwrirrv4nf2s6xxq

Hybrid Multi-layered GMDH-type Neural Network Using Principal Component Regression Analysis and its Application to Medical Image Diagnosis of Liver Cancer

Tadashi Kondo, Junji Ueno, Shoichiro Takao
2013 Procedia Computer Science  
These results are compared with the conventional sigmoid function neural network trained using the back propagation method, and this GMDH-type neural network algorithm is shown to be useful for CAD of  ...  , the radial basis function (RBF) network and the polynomial neural network architecture, by the heuristic self-organization method.  ...  Training data is used for estimating parameters of partial descriptions which describe partial relationships of the nonlinear system.  ... 
doi:10.1016/j.procs.2013.09.093 fatcat:v6dfc5ven5gbljuug4amnq4sk4

Inferring Static Non-monotone Size-aware Types Through Testing

Ron van Kesteren, Olha Shkaravska, Marko van Eekelen
2008 Electronical Notes in Theoretical Computer Science  
We propose a size analysis procedure that combines testing and type checking to automatically obtain static output-on-input size dependencies for first-order functions.  ...  For terminating functions, our size-aware type inference procedure is complete with respect to type checking: if a function is well-typed, then the inference procedure terminates and produces corresponding  ...  Higher-order functions A natural extension of our first-order analysis is to allow higher-order functions.  ... 
doi:10.1016/j.entcs.2008.06.033 fatcat:kbqg5uougzcz5gxex2ydb2rusq

Quasi-friendly sup-interpretations [article]

Jean-Yves Marion, Romain Pechoux
2006 arXiv   pre-print
In this former work, a criterion, which can be applied to terminating as well as non-terminating programs, was developed in order to bound polynomially the stack frame size.  ...  In a previous paper, the sup-interpretation method was proposed as a new tool to control memory resources of first order functional programs with pattern matching by static analysis.  ...  termination automatically.  ... 
arXiv:cs/0608020v1 fatcat:kpeyzrmfvfee7mhkdhian3wcom

Termination Analysis of Programs with Multiphase Control-Flow

Jesús J. Domenech, Samir Genaim
2021 Electronic Proceedings in Theoretical Computer Science  
In this paper we discuss techniques for proving termination of such programs, in particular: (1) using multiphase ranking functions, where we will discuss theoretical aspects of such ranking functions  ...  for several kinds of program representations; and (2) using control-flow refinement, in particular partial evaluation of Constrained Horn Clauses, to simplify the control-flow allowing, among other things  ...  Moreover, they developed heuristics for automatically configuring partial evaluation (i.e., inferring properties to guides specialisation) in order to achieve the desired CFR.  ... 
doi:10.4204/eptcs.344.2 fatcat:yugingmb3zafxmdrthxxqkisy4

Proof Theory at Work: Complexity Analysis of Term Rewrite Systems [article]

Georg Moser
2009 arXiv   pre-print
Moreover the majority of the presented work deals with the "automation" of such a complexity analysis.  ...  Must any termination order used for proving termination of the Battle of Hydra and Hercules-system have the Howard ordinal 1 as its order type?  ...  Cichon [36] discussed (and investigated) whether the complexity of a rewrite system for which termination is provable using a termination ordering of order type α is eventually dominated by a function  ... 
arXiv:0907.5527v2 fatcat:jxonbatpw5hdlabp5z7swfrgdy

Automated termination proofs with measure functions [chapter]

Jürgen Giesl
1995 Lecture Notes in Computer Science  
To overcome these drawbacks we introduce a calculus for automated termination proofs which is able to handle arbitrary measure functions based on polynomial norms.  ...  This paper deals with the automation of termination proofs for recursively de ned algorithms (i.e. algorithms in a pure functional language).  ...  Acknowledgements I would like to thank J urgen Brauburger, Stefan Gerberding, Thomas Kolbe, Martin Protzen, Christoph Walther and the referees for helpful comments.  ... 
doi:10.1007/3-540-60343-3_33 fatcat:no3adete5fdb3atqlgu2r6dizi

Automatic Static Cost Analysis for Parallel Programs [chapter]

Jan Hoffmann, Zhong Shao
2015 Lecture Notes in Computer Science  
This article introduces the first automatic analysis for deriving bounds on the worst-case evaluation cost of parallel first-order functional programs.  ...  The derived bounds are multivariate resource polynomials which depend on the sizes of the arguments of a function. Type inference can be reduced to linear programming and is fully automatic.  ...  This article introduces an automatic type-based resource analysis for the derivation of cost bounds for parallel first-order functional programs.  ... 
doi:10.1007/978-3-662-46669-8_6 fatcat:l4ieqjjnzrf4bdp7mwbzidguwu

Page 1646 of Mathematical Reviews Vol. , Issue 83d [page]

1983 Mathematical Reviews  
Second-order error estimates are proven for spatial discretization using conforming or nonconforming elements.  ...  An efficient algorithm for the evaluation of these basis functions and the control is presented and the use of the control is demonstrated using numerical examples.  ... 
« Previous Showing results 1 — 15 out of 28,732 results