Advanced mathematical analysis (2007)
A subject guide for external study students at the University of London
Advanced mathematical analysis (2007)
A subject guide for external study students at the University of London
Maximal width learning of binary functions (2006)
Anthony, Martin, Ratsaby, Joel
This paper concerns learning binary-valued functions defined on IR, and investigates how a particular type of ‘regularity’ of hypotheses can be used to obtain better generalization error bounds....
Connections between neural networks and boolean functions (2005)
This report surveys some connections between Boolean functions and artificial neural networks. The focus is on cases in which the individual neurons are linear threshold neurons, sigmoid neurons,...
Learning boolean functions (2005)
This report surveys some key results on the learning of Boolean functions in a probabilistic model that is a generalization of the well-known ‘PAC’ model.
This report is an exposition of decision lists and threshold decision lists. The key areas explored are the representation of Boolean functions by decision lists and threshold decision lists;...
Using a similarity measure for credible classification (2005)
Anthony, Martin, Hammer, P. L., Subasi, E., Subasi, M.
This paper concerns classification by Boolean functions. We investigate the classification accuracy obtained by standard classification techniques on unseen points (elements of the domain, {0, 1}n,...
On Boolean combinations of definitive classifiers (2003)
We consider the sample complexity of concept learning when we classify by using a fixed Boolean function of the outputs of a number of different classifiers. Here, we take into account the...
Franco, Leonardo, Anthony, Martin
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...
Margin-based generalization error bounds for threshold decision lists (2003)
This paper concerns the use of threshold decision lists for classifying data into two classes. The use of such methods has a natural geometrical interpretation and can be appropriate for an iterative...
Boolean functions and artificial neural networks (2003)
This report surveys some connections between Boolean functions and artificial neural networks. The focus is on cases in which the individual neurons are linear threshold neurons, sigmoid neurons,...
Links between learning and optimization: a brief tutorial (2003)
This report is a brief exposition of some of the important links between machine learning and combinatorial optimization. We explain how efficient ‘learnability’ in standard probabilistic models...
Learning multivalued multithreshold functions (2003)
This paper concerns multivalued multithreshold functions, {0, 1, . . . , k}-valued functions on Rn that may be considered as generalizations of (linear) threshold functions, or as discretized...
Matemáticas para la economía y las finanzas (2001)
Anthony, Martin, Biggs, Norman
Traducción de: Mathematics for Economics and Finance. Methods and Modelling
Discrete Mathematics of Neural Networks (2001)
Contenido: Redes neurales artificiales; Funciones booleanas; Funciones de umbral; Números de funciones de umbral; Tamaños y pesos para las funciones de umbral; Orden del umbral; Redes de umbral y...
Mathematics for Economics and Finance (1996)
Anthony, Martin, Biggs, Norman
Introducción al cálculo y álgebra lineal para estudiantes de disciplinas económicas y administrativas.
Valid Generalisation of Functions from Close Approximations on a Sample (1994)
Anthony, Martin, Shawe-Taylor, John
This volume contains 17 of the contributed papers presented at the 1st European Conference on Computational Learning Theory. Also included are invited presentations on the complexity of learning on...