The Experts below are selected from a list of 5484 Experts worldwide ranked by ideXlab platform
Zarita Zainuddin - One of the best experts on this subject based on the ideXlab platform.
-
FSKD - Triangular type-2 fuzzy neural networks version of the Stone-Weierstrass Theorem
2013 10th International Conference on Fuzzy Systems and Knowledge Discovery (FSKD), 2013Co-Authors: Saeed Panahian Fard, Zarita ZainuddinAbstract:The universal approximation capability of type-2 fuzzy neural networks plays an important role in the approximation theory of type-2 fuzzy neural networks. In this study, we propose a triangular type-2 fuzzy number by using the interval type-2 triangular fuzzy number as introduced in our previous work. Moreover, we introduce some triangular type-2 fuzzy operations. Then, we use these concepts to construct three layer feedforward triangular type-2 fuzzy neural networks. Furthermore, we establish a main Theorem that shows the universal approximation capability of these networks. The main Theorem can be regarded as the triangular type-2 fuzzy neural networks version of the Stone-Weierstrass Theorem.
-
Interval type-2 fuzzy neural networks version of the Stone-Weierstrass Theorem
Neurocomputing, 2011Co-Authors: Saeed Panahian Fard, Zarita ZainuddinAbstract:The main purpose of this study is to state conditions that guarantee an interval type-2 triangular fuzzy (IT2TF) neural network can approximate continuous IT2TF functions. To make a more efficient calculation with IT2TF numbers, the sum and the product of two IT2TF numbers are constructed. These concepts are used in the definition of IT2TF polynomials. Moreover, the present study provides a mathematical framework to show that IT2TF polynomials are a compact Hausdroff space. Based on this concept we establish an interval type-2 fuzzy neural networks version of the Stone-Weierstrass Theorem which enables approximation by a special class of IT2TF neural networks on the set of all monotonic and continuous IT2TF functions. Finally, a numerical example is given to illustrate the results.
Saeed Panahian Fard - One of the best experts on this subject based on the ideXlab platform.
-
FSKD - Triangular type-2 fuzzy neural networks version of the Stone-Weierstrass Theorem
2013 10th International Conference on Fuzzy Systems and Knowledge Discovery (FSKD), 2013Co-Authors: Saeed Panahian Fard, Zarita ZainuddinAbstract:The universal approximation capability of type-2 fuzzy neural networks plays an important role in the approximation theory of type-2 fuzzy neural networks. In this study, we propose a triangular type-2 fuzzy number by using the interval type-2 triangular fuzzy number as introduced in our previous work. Moreover, we introduce some triangular type-2 fuzzy operations. Then, we use these concepts to construct three layer feedforward triangular type-2 fuzzy neural networks. Furthermore, we establish a main Theorem that shows the universal approximation capability of these networks. The main Theorem can be regarded as the triangular type-2 fuzzy neural networks version of the Stone-Weierstrass Theorem.
-
Interval type-2 fuzzy neural networks version of the Stone-Weierstrass Theorem
Neurocomputing, 2011Co-Authors: Saeed Panahian Fard, Zarita ZainuddinAbstract:The main purpose of this study is to state conditions that guarantee an interval type-2 triangular fuzzy (IT2TF) neural network can approximate continuous IT2TF functions. To make a more efficient calculation with IT2TF numbers, the sum and the product of two IT2TF numbers are constructed. These concepts are used in the definition of IT2TF polynomials. Moreover, the present study provides a mathematical framework to show that IT2TF polynomials are a compact Hausdroff space. Based on this concept we establish an interval type-2 fuzzy neural networks version of the Stone-Weierstrass Theorem which enables approximation by a special class of IT2TF neural networks on the set of all monotonic and continuous IT2TF functions. Finally, a numerical example is given to illustrate the results.
Li-xin Wang - One of the best experts on this subject based on the ideXlab platform.
-
fuzzy basis functions universal approximation and orthogonal least squares learning
IEEE Transactions on Neural Networks, 1992Co-Authors: Li-xin Wang, Jerry M MendelAbstract:Fuzzy systems are represented as series expansions of fuzzy basis functions which are algebraic superpositions of fuzzy membership functions. Using the Stone-Weierstrass Theorem, it is proved that linear combinations of the fuzzy basis functions are capable of uniformly approximating any real continuous function on a compact set to arbitrary accuracy. Based on the fuzzy basis function representations, an orthogonal least-squares (OLS) learning algorithm is developed for designing fuzzy systems based on given input-output pairs; then, the OLS algorithm is used to select significant fuzzy basis functions which are used to construct the final fuzzy system. The fuzzy basis function expansion is used to approximate a controller for the nonlinear ball and beam system, and the simulation results show that the control performance is improved by incorporating some common-sense fuzzy control rules. >
-
Fuzzy systems are universal approximators
[1992 Proceedings] IEEE International Conference on Fuzzy Systems, 1992Co-Authors: Li-xin WangAbstract:The author proves that fuzzy systems are universal approximators. The Stone-Weierstrass Theorem is used to prove that fuzzy systems with product inference, centroid defuzzification, and a Gaussian membership function are capable of approximating any real continuous function on a compact set to arbitrary accuracy. This result can be viewed as an existence Theorem of an optimal fuzzy system for a wide variety of problems. >
B. Banaschewski - One of the best experts on this subject based on the ideXlab platform.
-
f-Rings and the Stone-Weierstrass Theorem
Order, 2001Co-Authors: B. BanaschewskiAbstract:Using an appropriate notion of separating subring, it is shown that the classical Stone-Weierstrass Theorem for compact Hausdorff spaces is ultimately a result about f -rings. As an application the constructively valid Stone-Weierstrass Theorem for compact completely regular frames is obtained.
-
A constructive proof of the Stone-Weierstrass Theorem
Journal of Pure and Applied Algebra, 1997Co-Authors: B. Banaschewski, Christopher J. MulveyAbstract:Abstract A constructive version of the Stone-Weierstrass Theorem is proved, allowing a globalisation of the Gelfand duality Theorem to any Grothendieck topos to be established elsewhere.
Gabriel Peyré - One of the best experts on this subject based on the ideXlab platform.
-
universal invariant and equivariant graph neural networks
Neural Information Processing Systems, 2019Co-Authors: Nicolas Keriven, Gabriel PeyréAbstract:Graph Neural Networks (GNN) come in many flavors, but should always be either invariant (permutation of the nodes of the input graph does not affect the output) or \emph{equivariant} (permutation of the input permutes the output). In this paper, we consider a specific class of invariant and equivariant networks, for which we prove new universality Theorems. More precisely, we consider networks with a single hidden layer, obtained by summing channels formed by applying an equivariant linear operator, a pointwise non-linearity, and either an invariant or equivariant linear output layer. Recently, Maron et al. (2019) showed that by allowing higher-order tensorization inside the network, universal invariant GNNs can be obtained. As a first contribution, we propose an alternative proof of this result, which relies on the Stone-Weierstrass Theorem for algebra of real-valued functions. Our main contribution is then an extension of this result to the \emph{equivariant} case, which appears in many practical applications but has been less studied from a theoretical point of view. The proof relies on a new generalized Stone-Weierstrass Theorem for algebra of equivariant functions, which is of independent interest. Additionally, unlike many previous works that consider a fixed number of nodes, our results show that a GNN defined by a single set of parameters can approximate uniformly well a function defined on graphs of varying size.
-
universal invariant and equivariant graph neural networks
arXiv: Learning, 2019Co-Authors: Nicolas Keriven, Gabriel PeyréAbstract:Graph Neural Networks (GNN) come in many flavors, but should always be either invariant (permutation of the nodes of the input graph does not affect the output) or equivariant (permutation of the input permutes the output). In this paper, we consider a specific class of invariant and equivariant networks, for which we prove new universality Theorems. More precisely, we consider networks with a single hidden layer, obtained by summing channels formed by applying an equivariant linear operator, a pointwise non-linearity and either an invariant or equivariant linear operator. Recently, Maron et al. (2019) showed that by allowing higher-order tensorization inside the network, universal invariant GNNs can be obtained. As a first contribution, we propose an alternative proof of this result, which relies on the Stone-Weierstrass Theorem for algebra of real-valued functions. Our main contribution is then an extension of this result to the equivariant case, which appears in many practical applications but has been less studied from a theoretical point of view. The proof relies on a new generalized Stone-Weierstrass Theorem for algebra of equivariant functions, which is of independent interest. Finally, unlike many previous settings that consider a fixed number of nodes, our results show that a GNN defined by a single set of parameters can approximate uniformly well a function defined on graphs of varying size.
-
NeurIPS - Universal Invariant and Equivariant Graph Neural Networks
2019Co-Authors: Nicolas Keriven, Gabriel PeyréAbstract:Graph Neural Networks (GNN) come in many flavors, but should always be either invariant (permutation of the nodes of the input graph does not affect the output) or \emph{equivariant} (permutation of the input permutes the output). In this paper, we consider a specific class of invariant and equivariant networks, for which we prove new universality Theorems. More precisely, we consider networks with a single hidden layer, obtained by summing channels formed by applying an equivariant linear operator, a pointwise non-linearity, and either an invariant or equivariant linear output layer. Recently, Maron et al. (2019) showed that by allowing higher-order tensorization inside the network, universal invariant GNNs can be obtained. As a first contribution, we propose an alternative proof of this result, which relies on the Stone-Weierstrass Theorem for algebra of real-valued functions. Our main contribution is then an extension of this result to the \emph{equivariant} case, which appears in many practical applications but has been less studied from a theoretical point of view. The proof relies on a new generalized Stone-Weierstrass Theorem for algebra of equivariant functions, which is of independent interest. Additionally, unlike many previous works that consider a fixed number of nodes, our results show that a GNN defined by a single set of parameters can approximate uniformly well a function defined on graphs of varying size.