The influence of opposite examples and randomness on the generalization complexity of Boolean functions
نویسندگان
چکیده
We analyze Boolean functions using a recently proposed measure of their complexity. This complexity measure, motivated by the aim of relating the complexity of the functions with the generalization ability that can be obtained when the functions are implemented in feed-forward neural networks, is the sum of two components. The first of these is related to the ‘average sensitivity’ of the function and the second is, in a sense, a measure of the ‘randomness’ or lack of structure of the function. In this paper, we investigate the importance of using the second term in the complexity measure. We also explore the existence of very complex Boolean functions, considering, in particular, the symmetric Boolean functions. e-mail: [email protected], Tel.: +44-(0)1865-271419, Fax: +44-(0)1865-310447 email: [email protected], Tel.: +44-(0)207-9557623, Fax: +44-(0)207-9556877 1
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 کاملON THE FUZZY SET THEORY AND AGGREGATION FUNCTIONS: HISTORY AND SOME RECENT ADVANCES
Several fuzzy connectives, including those proposed by Lotfi Zadeh, can be seen as linear extensions of the Boolean connectives from the scale ${0,1}$ into the scale $[0,1]$. We discuss these extensions, in particular, we focus on the dualities arising from the Boolean dualities. These dualities allow to transfer the results from some particular class of extended Boolean functions, e.g., from c...
متن کاملA measure for the complexity of Boolean functions related to their implementation in neural networks
We define a measure for the complexity of Boolean functions related to their implementation in neural networks, and in particular close related to the generalization ability that could be obtained through the learning process. The measure is computed through the calculus of the number of neighbor examples that differ in their output value. Pairs of these examples have been previously shown to b...
متن کاملGeneralization ability of Boolean functions implemented in feedforward neural networks
We introduce a measure for the complexity of Boolean functions that is highly correlated with the generalization ability that could be obtained when the functions are implemented on feedforward neural networks. The measure, based on the calculation of the number of neighbour examples that differ in their output value, can be simple computed from the definition of the functions, independently of...
متن کاملNew Generalization of Darbo's Fixed Point Theorem via $alpha$-admissible Simulation Functions with Application
In this paper, at first, we introduce $alpha_{mu}$-admissible, $Z_mu$-contraction and $N_{mu}$-contraction via simulation functions. We prove some new fixed point theorems for defined class of contractions via $alpha$-admissible simulation mappings, as well. Our results can be viewed as extension of the corresponding results in this area. Moreover, some examples and an application to funct...
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 2003