The problem of representing temporal knowledge arises in many areas of computer science. In applications in which such knowledge is imprecise or relative, current representations based on date lines or time instants are inadequate. An interval-based temporal logic is introduced, together WiUl a

The exact form of a gradient-following learning algorithm for completely recurrent networks running in continually sampled time is derived and used as the basis for practical algorithms for temporal supervised learning tasks. These algorithms have: (1) the advantage that they do not require a

Abstract Since most real-world applications of classification learning involve continuous-valued attributes, properly addressing the discretization process is an important problem. This paper addresses the use of the entropy minimization heuristic for discretizing the range of a continuous

formalism is very similar to temporal logics. This allows the language to be used for both writing programs and expressing program properties, which results in an original program verification methodology. 1 Introduction Reactive systems Reactive systems have been defined as computing systems which

, illumination and partial occlusion. The temporal continuity of the video within a shot is used to track the regions in order to reject unstable regions and reduce the effects of noise in the descriptors. The analogy with text retrieval is in the implementation where matches on descriptors are pre

A hybrid system is a dynamical system whose behavior exhibits both discrete and continuous change. A hybrid automaton is a mathematical model for hybrid systems, which combines, in a single formalism, automaton transitions for capturing discrete change with differential equations for capturing

), this model has no parameters which change over time and is able to continue learning, adding units and connections, until a performance criterion has been met. Applications of the model include vector quantization, clustering, and interpolation. 1 INTRODUCTION In unsupervised learning settings only input

A temporal database (see Temporal Database) contains time-varying data. Time is an important aspect of all real-world phenomena. Events occur at specific points in time; objects and the relationships among objects exist over time. The ability to model this temporal dimension of the real world

these methods to high dimensional continuous state-spaces, which requires the use of function approximation to generalise the information learnt by the system. In this report, the use of back-propagation neural networks (Rumelhart, Hinton and Williams 1986) is considered in this context. We consider a number

This paper extends to two dimensions the frame criterion developed by Daubechies for one-dimensional wavelets, and it computes the frame bounds for the particular case of 2D Gabor wavelets. Completeness criteria for 2D Gabor image representations are important because of their increasing role