Rates of approximation of real-valued boolean functions by neural networks
نویسندگان
چکیده
We give upper bounds on rates of approximation of real-valued functions of d Boolean variables by one-hidden-layer perceptron networks. Our bounds are of the form c/n where c depends on certain norms of the function being approximated and n is the number of hidden units. We describe sets of functions where these norms grow either polynomially or exponentially with d.
منابع مشابه
The ring of real-valued functions on a frame
In this paper, we define and study the notion of the real-valued functions on a frame $L$. We show that $F(L) $, consisting of all frame homomorphisms from the power set of $mathbb{R}$ to a frame $ L$, is an $f$-ring, as a generalization of all functions from a set $X$ into $mathbb R$. Also, we show that $F(L) $ is isomorphic to a sub-$f$-ring of $mathcal{R}(L)$, the ring of real-valued continu...
متن کاملMin-max classifiers: Learnability, design and application
This paper introduces the class of min max classifiers. These are binary-valued functions that can be used as pattern classifiers of both real-valued and binary-valued feature vectors. They are also lattice-theoretic generalization of Boolean functions and are also related to feed-forward neural networks and morphological signal operators. We studied supervised learning of these classifiers und...
متن کاملAdvances in Neural Networks
PREFACE Artificial neural networks or simply neural networks represent an emerging technology rooted in many disciplines. This popular and important area of science and technology was extensively developing for the recent period of time. Neural networks are endowed with some unique attributes, like the ability to learn from and adapt to their environment and the ability to approximate very comp...
متن کاملOn Robust Concepts and Small Neural Nets
The universal approximation theorem for neural networks says that any reasonable function is well-approximated by a two-layer neural network with sigmoid gates but it does not provide good bounds on the number of hidden-layer nodes or the weights. However, robust concepts often have small neural networks in practice. We show an efficient analog of the universal approximation theorem on the bool...
متن کاملA vector matrix real time backpropagation algorithm for recurrent neural networks that approximate multi-valued periodic functions
A vector matrix real time backpropagation algorithm for recurrent neural networks that approximate multi-valued periodic functions," Received Unlike feedforward neural networks (FFNN) which can act as universal function ap-proximators, recursive, or recurrent, neural networks can act as universal approximators for multi-valued functions. In this paper, a real time recursive backpropagation (RTR...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- Neural networks : the official journal of the International Neural Network Society
دوره 11 4 شماره
صفحات -
تاریخ انتشار 1996