-Template matching is a fundamental technique of pattern recognition. Although this technique is very general, its applicability has been limited because of the difficulty often encountered when fitting templates to natural data. Natural patterns are often distorted, misshapen, stretched in size, fuzzy, rotated, translated, observed at an unusual perspective, etc. Flexible templates (rubber mas...

In this paper we discuss how Fibonacci growth patterns are apparent in the structure of human language. We moreover show how familiar dynamics yielding these sorts of patterns in nature may be taken to apply, at some level of abstraction, for the human faculty of language. The overall picture casts doubts on any simplistic treatment of language behavior, of the sort stemming from classical beha...

Spontaneous symmetry breaking can result in emergence of complicated patterns in nature. Simple symmetry arguments can be used to describe beautiful and periodic rippled and wavy edges of flowers and leaves as well as fractal structure at the edge of a torn plastic sheet. In this paper, I will first discuss simple physical and geometrical arguments based on symmetry breaking and metrics on a cu...

We consider the classic puzzle of why people turn out for elections in substantial numbers even though formal analysis strongly suggests that rational agents would not vote. If one assumes that voters do not make systematic mistakes, the most plausible explanation seems to be that agents receive a warm glow from the act of voting itself. However, this begs the question of why agents feel a warm...

We propose a method for synthesising head motion from speech using a combination of an Input-Output Markov model (IOMM) and Gaussian mixture models trained in a supervised manner. A key difference of this approach compared to others is to model the head motion in each angle as a series of templates of motion rather than trying to recover a frame-wise function. The templates were chosen to refle...

Humans are sensitive to complexity and regularity in patterns [YKM13, FK97]. The subjective perception of pattern complexity is correlated to algorithmic (Kolmogorov-Chaitin) complexity as defined in computer science [LV08], but also to the frequency of naturally occurring patterns [HGS10]. However, the possible mediational role of natural frequencies in the perception of algorithmic complexity...