The major problem when building shape models by minimising the description length (DL) is the computationally demanding optimisation in a highdimensional space. To speed up the convergence when dealing with discretised contours, Ericsson and Åström [6] have shown how to approximate and how to exploit the gradient of the DL. We derive the gradient of the DL for differentiable training sets. Addi...

Developing robust and reliable control code for autonomous mobile robots is difficult, because the interaction between a physical robot and the environment is highly complex, subject to noise and variation, and therefore partly unpredictable. This means that to date it is not possible to predict robot behaviour based on theoretical models. Instead, current methods to develop robot control code ...

We find an explicit expression of the Tutte polynomial of an $n$-fan. We also find a formula of the Tutte polynomial of an $n$-wheel in terms of the Tutte polynomial of $n$-fans. Finally, we give an alternative expression of the Tutte polynomial of an $n$-wheel and then prove the explicit formula for the Tutte polynomial of an $n$-wheel.

OBJECTIVE Variability in infant sleep and negative affective behavior (NAB) is a developmental phenomenon that has long been of interest to researchers and clinicians. However, analyses and delineation of such temporal patterns were often limited to basic statistical approaches, which may prevent adequate identification of meaningful variation within these patterns. Modern statistical procedure...

In present study, a three-step multi-objective optimization algorithm of cyclone separators is catered for the design objectives. First, the pressure drop (Dp) and collection efficiency (h) in a set of cyclone separators are numerically evaluated. Secondly, two meta models based on the evolved Group Method of Data Handling (GMDH) type neural networks are regarded to model the Dp and h as the re...

In this paper a data simulation system, based on the cos(x) and sin(x)/x functions, called CSINC Polynomial Higher Order Neural Network (CSINCPHONN) has been developed. The CSINCPHONN model provides one more opportunity to find the optimal neural network model for simulation and prediction. This paper also proves that CSINCPHONN models can converge when simulating XOR data. This study also test...

The use of higher-order polynomial acoustic features can improve the performance of automatic speech recognition. However, the dimensionality of the polynomial representation can be prohibitively large, making the training of acoustic models using polynomial features for large vocabulary ASR systems infeasible. This paper presents an iterative polynomial training framework for acoustic modeling...