Search results for "Machine learning"
showing 10 items of 1464 documents
Support vector machines in engineering: an overview
2014
This paper provides an overview of the support vector machine SVM methodology and its applicability to real-world engineering problems. Specifically, the aim of this study is to review the current state of the SVM technique, and to show some of its latest successful results in real-world problems present in different engineering fields. The paper starts by reviewing the main basic concepts of SVMs and kernel methods. Kernel theory, SVMs, support vector regression SVR, and SVM in signal processing and hybridization of SVMs with meta-heuristics are fully described in the first part of this paper. The adoption of SVMs in engineering is nowadays a fact. As we illustrate in this paper, SVMs can …
Memory limited inductive inference machines
1992
The traditional model of learning in the limit is restricted so as to allow the learning machines only a fixed, finite amount of memory to store input and other data. A class of recursive functions is presented that cannot be learned deterministically by any such machine, but can be learned by a memory limited probabilistic leaning machine with probability 1.
Organized Learning Models (Pursuer Control Optimisation)
1982
Abstract The concept of Organized Learning is defined, and some random models are presented. For Not Transferable Learning, it is necessary to start from an instantaneous learning; by a discrete way, we must form a stochastic model considering the probability of each path; with a continue aproximation, we can study the evolution of the internal state through to consider the relative and absolute probabilities, by means of differential equations systems. For Transferable Learning, the instantaneous learning give us directly the System evolution. So, the Algoritmes for the different models are compared.
Empirical Evaluation of the Bayesian Learning Automaton Family
2009
Masteroppgave i informasjons- og kommunikasjonsteknologi 2009 – Universitetet i Agder, Grimstad The two-armed bandit problem is a classical optimization problem where a player sequentially selects and pulls one of two arms attached to a gambling machine, and each arm pull results in either a reward or penalty to the player. Each arm is associated with a certain reward probability which is unknown to the player, and the player needs to sequentially select and play an arm and receive a reward or a penalty in order to discover its true reward probability. The overall goal for the player is reward maximization, and the player needs to balance between exploiting existing knowledge or obtaining n…
SVM approximation for real-time image segmentation by using an improved hyperrectangles-based method
2003
A real-time implementation of an approximation of the support vector machine (SVM) decision rule is proposed. This method is based on an improvement of a supervised classification method using hyperrectangles, which is useful for real-time image segmentation. The final decision combines the accuracy of the SVM learning algorithm and the speed of a hyperrectangles-based method. We review the principles of the classification methods and we evaluate the hardware implementation cost of each method. We present the combination algorithm, which consists of rejecting ambiguities in the learning set using SVM decision, before using the learning step of the hyperrectangles-based method. We present re…
Rational irreducible characters and rational conjugacy classes in finite groups
2007
We prove that a finite group G G has two rational-valued irreducible characters if and only if it has two rational conjugacy classes, and determine the structure of any such group. Along the way we also prove a conjecture of Gow stating that any finite group of even order has a non-trivial rational-valued irreducible character of odd degree.
Homology of pseudodifferential operators on manifolds with fibered cusps
2003
The Hochschild homology of the algebra of pseudodifferential operators on a manifold with fibered cusps, introduced by Mazzeo and Melrose, is studied and computed using the approach of Brylinski and Getzler. One of the main technical tools is a new convergence criterion for tri-filtered half-plane spectral sequences. Using trace-like functionals that generate the 0 0 -dimensional Hochschild cohomology groups, the index of a fully elliptic fibered cusp operator is expressed as the sum of a local contribution of Atiyah-Singer type and a global term on the boundary. We announce a result relating this boundary term to the adiabatic limit of the eta invariant in a particular case.
Understanding star-fundamental algebras
2021
Star-fundamental algebras are special finite dimensional algebras with involution ∗ * over an algebraically closed field of characteristic zero defined in terms of multialternating ∗ * -polynomials. We prove that the upper-block matrix algebras with involution introduced in Di Vincenzo and La Scala [J. Algebra 317 (2007), pp. 642–657] are star-fundamental. Moreover, any finite dimensional algebra with involution contains a subalgebra mapping homomorphically onto one of such algebras. We also give a characterization of star-fundamental algebras through the representation theory of the symmetric group.
Thompson Sampling for Dynamic Multi-armed Bandits
2011
The importance of multi-armed bandit (MAB) problems is on the rise due to their recent application in a large variety of areas such as online advertising, news article selection, wireless networks, and medicinal trials, to name a few. The most common assumption made when solving such MAB problems is that the unknown reward probability theta k of each bandit arm k is fixed. However, this assumption rarely holds in practice simply because real-life problems often involve underlying processes that are dynamically evolving. In this paper, we model problems where reward probabilities theta k are drifting, and introduce a new method called Dynamic Thompson Sampling (DTS) that facilitates Order St…
Fuzzy Clustering of Histopathological Images Using Deep Learning Embeddings
2021
Metric learning is a machine learning approach that aims to learn a new distance metric by increas- ing (reducing) the similarity of examples belonging to the same (different) classes. The output of these approaches are embeddings, where the input data are mapped to improve a crisp or fuzzy classifica- tion process. The deep metric learning approaches regard metric learning, implemented by using deep neural networks. Such models have the advantage to discover very representative nonlinear embed- dings. In this work, we propose a triplet network deep metric learning approach, based on ResNet50, to find a representative embedding for the unsupervised fuzzy classification of benign and maligna…