Computationally Efficient Invariant Pattern Recognition with Higher Order Pi-sigma Networks1
نویسنده
چکیده
A class of higher-order networks called Pi-Sigma networks has recently been introduced for function approximation and classiication 4]. These networks combine the fast training abilities of single-layered feedforward networks with the non-linear mapping of higher-order networks, while using much fewer number of units. In this paper, we investigate the applicability of these networks for shift, scale and rotation invariant pattern recognition. Results obtained using a database of English and Persian characters compare favorably with other neural network based approaches 2, 3].
منابع مشابه
How to make sigma-pi neural networks perform perfectly on regular training sets
Abstract--In this paper, we show how to design three-layer feedforward neural networks with sigma-pi units in the hidden layer in order to perform perfectly on regular training sets. We obtain real-time design schemes based on massively parallel sampling and induced by so-called hyperbolic cardinal translation-type interpolation operators. The real-time nature of our strategy is due to the fact...
متن کاملTwo-dimensional Object Recognition Based on the Method of Moving Frame
Invariant features play a key role in object and pattern recognition studies. Features that are invariant to geometrical transformations offer succinct representations of underlying objects so that they can be reliably identified. In this paper, a family of novel invariant features is introduced based on Cartan’s theory of moving frames. These new features is called summation invariants. Compar...
متن کاملSolving Time of Least Square Systems in Sigma-Pi Unit Networks
− The solving of least square systems is a useful operation in neurocomputational modeling of learning, pattern matching, and pattern recognition. In these last two cases, the solution must be obtained on-line, thus the time required to solve a system in a plausible neural architecture is critical. This paper presents a recurrent network of Sigma-Pi neurons, whose solving time increases at most...
متن کاملHygrothermal Analysis of Laminated Composite Plates by Using Efficient Higher Order Shear Deformation Theory
Hygrothermal analysis of laminated composite plates has been done by using an efficient higher order shear deformation theory. The stress field derived from hygrothermal fields must be consistent with total strain field in this type of analysis. In the present formulation, the plate model has been implemented with a computationally efficient C0 finite element developed by using consistent strai...
متن کاملPractical, Computation Efficient High-order Neural Network for Rotation and Shift Invariant Pattern Recognition
In this paper, a modification for the high-order neural network (HONN) is presented. Third order networks are considered for achieving translation, rotation and scale invariant pattern recognition. They require however much storage and computation power for the task. The proposed modified HONN takes into account a priori knowledge of the binary patterns that have to be learned, achieving signif...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1992