Wyniki wyszukiwania - BazTech

1

The recognition of partially occluded objects with support vector machines, convolutional neural networks and deep belief networks

Chu J. L., Krzyżak A.

Journal of Artificial Intelligence and Soft Computing Research

|

2014

|

Vol. 4, No. 1

5--19

EN

Biologically inspired artificial neural networks have been widely used for machine learning tasks such as object recognition. Deep architectures, such as the Convolutional Neural Network, and the Deep Belief Network have recently been implemented successfully for object recognition tasks. We conduct experiments to test the hypothesis that certain primarily generative models such as the Deep Belief Network should perform better on the occluded object recognition task than purely discriminative models such as Convolutional Neural Networks and Support Vector Machines. When the generative models are run in a partially discriminative manner, the data does not support the hypothesis. It is also found that the implementation of Gaussian visible units in a Deep Belief Network trained on occluded image data allows it to also learn to effectively classify non-occluded images.

2

Concept of Usage of Bayesian Networks in Clinical Decision Support Module

Strawa M.

Biuletyn Instytutu Systemów Informatycznych

|

2012

|

nr 9

27-34

EN

Concept of decision support module utilizing a repository of clinical pathways has been presented in this paper: the definition of Bayesian networks and its major concepts, description of chosen inference algorithm and an example of diagnosis.

PL

W artykule przedstawiono koncepcję budowy modułu wspomagania decyzji medycznych, współpracującego z repozytorium ścieżek klinicznych. Składają się na nią: definicja sieci bayesowskich oraz najważniejszych pojęć z nimi związanych, opis wybranego mechanizmu wnioskowania oraz przykład generowania diagnozy w module.

3

Modele odwrotne i modelowanie diagnostyczne

Cholewa W.

Diagnostyka

|

2004

|

Vol. 30, T. 1

111--114

PL

Praca dotyczy ogólnej metodologii badań diagnostycznych, Wskazano podejścia bazujące na biernych i czynnych eksperymentach diagnostycznych. Zaproponowano podejście mieszane, w którym stosowane są modele odwrotne współdziałające ze szczególnymi układami wnioskującymi wykonanymi z zastosowaniem sieci przekonań. Opracowanie zawiera ogólne wprowadzenie do modeli odwrotnych oraz do sieci przekonań.

EN

The paper deals with a general methodology for diagnostic investigations. It presents basic approaches connected with passive as well as active diagnostic experiments. It suggests a mixed approach making use of inverse models followed by a particular diagnostic reasoning done by means of belief networks. The paper contains a basic introduction to the inverse models and to belief networks.

4

The role of time in influence diagrams

Traczyk W.

Journal of Telecommunications and Information Technology

|

2003

|

nr 3

108-111

EN

An influence diagram is a compact representation emphasizing the qualitative features of decision problem under uncertainty. Classical influence diagram has parameters stable in time, determined order of suggested decisions and generally is independent of time. Here we have shown some possible methods of construction of time dependent influence diagrams: with decision ordering, time-sliced segments and time consuming nodes. Such gathering of methods can help in selection of a proper solution.

5

On a deficiency of the FCI algorithm learning Bayesian from data

Kłopotek M.

Demonstratio Mathematica

|

2000

|

Vol. 33, nr 1

181-194

EN

Causally insufficient structures (models with latent or hidden variables, or with confounding etc.) of joint probability distributions have been subject of intense study not oniy in statistics, but also in various AI systems. In AI, belief networks, being representations of joint probability distribution with an underlying directed acyclic graph structure, are paid special attention due to the fact that efficient reasoning (uncertainty propagation) methods have been developed for belief network structures. Algorithms have been therefore developed to acquire the belief network structure from data. As artifacts due to variable hiding negatively influence the performance of derived belief networks, models with latent variables have been studied and several algorithms for learning belief network structure under causal insufficiency have also been developed. Regrettably, some of them are known aiready to be erroneous (e.g. IC algorithm of [12]). This paper is devoted to another algorithm, the Fast Causal Inference (FCI) Algorithm of [17]. It is proven by a specially constructed example that this algorithm, as it stands in [17], is also erroneous. Fundamental reason for failure of this algorithm is the temporary introduction of non-real links between nodes of the network with the intention of later removal. While for trivial dependency structures these non-real links may be actually removed, this may not be the case for complex ones, e.g. for the case described in this paper. A remedy of this failure is proposed

6

Fast restricted casual inference

Kłopotek M.

Demonstratio Mathematica

|

2000

|

Vol. 33, nr 2

419-442

EN

Hidden variables are well known sources of disturbance when recovering belief networks from data based oniy on measurable variables. Hence models assuming existence of hidden variables are under development. This paper presents a new algorithm "accelerating" the known CI algorithm of Spirtes, Glymour and Scheines [20]. We prove that this algorithm does not produces (conditional) independencies not present in the data if statistical independence test is reliable. This result is to be considered as non-trivial since e.g. the same claim fails to be true for FCI algorithm, another " accelerator" of CI, developed in [20].