...............................................................................................................................iii Acknowledgements.............................................................................................................. iv Table of

The number of parameters in a model and its ability to generalize on the underlying data-generating machinery are tightly coupled entities. Neural networks consist usually of a large number of parameters, and pruning (the process of setting single parameters to zero) has been used to reduce the nets complexity in order to increase its generalization ability. Another less obvious approach is to ...

The minimum description length(MDL) method is one of the pioneer methods of parametric order estimation with a wide range of applications. We investigate the definition of two-stage MDL for parametric linear model sets and exhibit some drawbacks of the theory behind the existing MDL. We introduce a new description length which is inspired by the Kolmogorov complexity principle.

In [12] we have shown that the standard de nition of compositionality is formally vacuous; that is, any semantics can be easily encoded as a compositional semantics. We have also shown that when compositional semantics is required to be "systematic", it is possible to introduce a non-vacuous concept of compositionality. However, a technical de nition of systematicity was not given in that paper...

Recent work in the field of computational evolutionary linguistics suggests that the dynamics arising from the cultural evolution of language can explain the emergence of syntactic structure. We build on this work by introducing a model of language acquisition based on the Minimum Description Length Principle. Our experiments show that compositional syntax is most likely to occur under two cond...

We present a method for automatically identifying verbal participation in diathesis alternations. Automatically acquired subcategorization frames are compared to a hand-crafted classification for selecting candidate verbs. The minimum description length principle is then used to produce a model and cost for storing the head noun instances from a training corpus at the relevant argument slots. A...

This paper proposes an Extended Minimum Description Length Principle (EMDLP) for feature-based inductive transfer learning, in which both the source and the target data sets contain class labels and relevant features are transferred from the source domain to the target one. Despite numerous works on this topic, few of them have a solid theoretical framework and are parameter-free. Our EMDLP ove...

Corners, T-, Y-, X-junctions give vital depth cues which is a critical aspect of image \understanding": junctions form an important class of features invaluable in most vision systems. The three main issues in a junction (or any feature) detector are: scale, location, and, the junction (feature) parameters. The junction parameters are (1) the radius, or size, of the junction, (2) the kind of ju...