Search results for "recursive"
showing 10 items of 64 documents
Memory limited inductive inference machines
1992
The traditional model of learning in the limit is restricted so as to allow the learning machines only a fixed, finite amount of memory to store input and other data. A class of recursive functions is presented that cannot be learned deterministically by any such machine, but can be learned by a memory limited probabilistic leaning machine with probability 1.
On the intrinsic complexity of learning
1995
A new view of learning is presented. The basis of this view is a natural notion of reduction. We prove completeness and relative difficulty results. An infinite hierarchy of intrinsically more and more difficult to learn concepts is presented. Our results indicate that the complexity notion captured by our new notion of reduction differs dramatically from the traditional studies of the complexity of the algorithms performing learning tasks.
On the inductive inference of recursive real-valued functions
1999
AbstractWe combine traditional studies of inductive inference and classical continuous mathematics to produce a study of learning real-valued functions. We consider two possible ways to model the learning by example of functions with domain and range the real numbers. The first approach considers functions as represented by computable analytic functions. The second considers arbitrary computable functions of recursive real numbers. In each case we find natural examples of learnable classes of functions and unlearnable classes of functions.
A fast recursive algorithm for the computation of axial moments
2002
This paper describes a fast algorithm to compute local axial moments used for the detection of objects of interest in images. The basic idea is grounded on the elimination of redundant operations while computing axial moments for two neighboring angles of orientation. The main result is that the complexity of recursive computation of axial moments becomes independent of the total number of computed moments in a given point, i.e. it is of the order O(N) where N is the data size. This result is of great importance in computer vision since many feature extraction methods are based on the computation of axial moments. The experimental results confirm the time complexity and accuracy predicted b…
Enhanced Current Loop PI Controllers with Adaptive Feed-Forward Neural Network via Estimation of Grid Impedance: Application to Three-Phase Grid-Tied…
2022
This paper describes a single-stage grid-connected three-phase photovoltaic inverter feeding power to the grid. Using the Recursive Least Squares (RLS) Estimator, an online grid impedance technique is proposed in the stationary reference frame. The method iteratively estimates the grid resistance and inductance values and is effective in detecting inverter islanding according to IEEE standard 929-2000. An Adaptive Feedforward Neural (AFN) Controller has also been developed using the inverse of the system to improve the performance of the inner-loop Proportional-Integral controllers under dynamical conditions and provide better DC link voltage stability. The neural network weights are comput…
Verification of Well-Formed Communicating Recursive State Machines
2008
AbstractIn this paper we introduce a new (non-Turing equivalent) formal model of recursive concurrent programs called well-formed communicating recursive state machines (CRSM). CRSM extend recursive state machines (RSM) by allowing a restricted form of concurrency: a state of a module can be refined into a finite collection of modules (working in parallel) in a potentially recursive manner. Communication is only possible between the activations of modules invoked on the same fork. We study the model-checking problem of CRSM with respect to specifications expressed in a temporal logic that extends CaRet with a parallel operator (ConCaRet). We propose a decision algorithm that runs in time ex…
On the Amount of Nonconstructivity in Learning Recursive Functions
2011
Nonconstructive proofs are a powerful mechanism in mathematics. Furthermore, nonconstructive computations by various types of machines and automata have been considered by e.g., Karp and Lipton [17] and Freivalds [11]. They allow to regard more complicated algorithms from the viewpoint of much more primitive computational devices. The amount of nonconstructivity is a quantitative characterization of the distance between types of computational devices with respect to solving a specific problem. In the present paper, the amount of nonconstructivity in learning of recursive functions is studied. Different learning types are compared with respect to the amount of nonconstructivity needed to lea…
Minimal nontrivial space complexity of probabilistic one- way turing machines
2005
Languages recognizable in o(log log n) space by probabilistic one — way Turing machines are proved to be regular. This solves an open problem in [4].
Double index recursive models
1994
The purpose of this document is to study the model belongs to the family of structural equation models with data varying both accross individuals (sectors) and in time. A complete theoretical analysis is developed in this work for the case of a recursive structure. Maximum likelihood estimation and Zellner's "seemingly unrelated equations" estimators (iterated or not) are presented and their asymptotic properties are carefully derived.The application of the estimation methods to the economy morocco produced statistically significant and economic meaningful results. Through a test of exogeneity, the recursivity of the system is confirmed. Policy recommendations are discussed and analyzed.
Mathematical Control of Complex Systems 2013
2014
Mathematical control of complex systems have already become an ideal research area for control engineers, mathematicians, computer scientists, and biologists to understand, manage, analyze, and interpret functional information/dynamical behaviours from real-world complex dynamical systems, such as communication systems, process control, environmental systems, intelligent manufacturing systems, transportation systems, and structural systems. This special issue aims to bring together the latest/innovative knowledge and advances in mathematics for handling complex systems. Topics include, but are not limited to the following: control systems theory (behavioural systems, networked control syste…