We introduce an efficient approach for representing a human face using a limited number of images. This compact representation allows for meaningful manipulation of the face. Principal Components Analysis (PCA) utilized in our research makes possible the separation of facial features so as to build statistical shape and texture models. Thus changing the model parameters can create images with d...

ii Abstract (in Finnish) iiiin Finnish) iii

We have proposed a novel probabilistic approach to concatenation modeling for corpus-based speech synthesis, where the goodness of concatenation for a unit is modeled using a conditional Gaussian probability density whose mean is defined as a linear transform of the feature vector from the previous unit. This approach has shown its effectiveness through a subjective listening test. In this pape...

In our earlier work, we found that feature space induced by tactile receptive fields (TRFs) are better than that by visual receptive fields (VRFs) in texture boundary detection tasks. This suggests that TRFs could be intimately associated with texture-like input. In this paper, we investigate how TRFs can develop in a cortical learning context. Our main hypothesis is that TRFs can be self-organ...

We propose a linearly penalized support vector machines (LP-SVM) model for feature selection. Its application to a problem of customer retention and a comparison with other feature selection techniques underlines its effectiveness.

Learning in automated negotiations, while useful, is hard because of the indirect way the target function can be observed and the limited amount of experience available to learn from. This paper proposes two novel opponent modeling techniques based on deep learning methods. Moreover, to improve the learning efficacy of negotiating agents, the second approach is also capable of transferring know...

Knowledge of the framework topology of zeolites is essential for multiple applications. Framework type determination relying on the combined information of coordination sequences and vertex symbols is appropriate for crystals with no defects. In this work we present an alternative machine learning model to classify zeolite crystals according to their framework types. The model is based on an ei...

In tkis paper, we analyze the class separation ofthefeatures in handwriting recognition. Behaviors of measurement tools are studied with partial and full class$cations. A new scheme ofselecting and combining class-dependentfeatures is proposed. In this scheme, a class is considered to have its own optimalfeature vectorfOr discriminating irselfSrom tke other classes. Using an architecture of mod...

Human motion can be understood on many levels. The most basic level is the notion that humans are collections of things that have predictable visual appearance. Next is the notion that humans exist in a physical universe, as a consequence of this, a large part of human motion can be modeled and predicted with the laws of physics. Finally there is the notion that humans utilize muscles to active...

Introduction: We present a discriminant power analysis framework that can be used in localizing the abnormal cortical thickness asymmetry pattern in a clinical group compared with a control group. In our example, we show that a group of high functioning autistic subjects has a cortical thickness asymmetry pattern that differs reliably from controls. Unlike previous literature, our approach does...