No description available.

No description available.

No description available.

No description available.

published_or_final_version / abstract / Computer Science / Master / Master of Philosophy

The ability to construct and manipulate recursive symbol structures is regarded as fundamentally important in the domain of cognitive modelling. The aim of this thesis dissertation is to explore how well Pollack's Recursive Auto-Associative Memory (RAAM) networks can represent and facilitate the manipulation of highly-recursive structures. Using mainly skewed and balanced binary trees, the representational power of the RAAM architecture is examined for structures which are lexically simple and syntactically complex. This is in contrast to much published work on RAAM networks, in which the structures encoded are lexically complex but syntactically simple. A new RAAM tree-processing operation, which allows partial information about a set of siblings to be used as a parent pointer, is described and tested. Several empirical investigations are motivated and carried out, to determine how effectively RAAM networks can encode highly-recursive structures. The investigations demonstrate the sensitivity of the RAAM architecture with respect to the initial conditions, training parameters and the training strategies used. This work also introduces some new techniques which help to address the twin problems of extended training times and obtaining successful RAAM encodings. A completely new method for performing terminal detection is presented as well as a technique for refining Pollack's (1990) terminal detection method. In both cases, the rate at which successful RAAM encodings are obtained is significantly better than using Pollack's method. In addition, the new implicit terminal detection method might allow improved RAAM generalisation, although this conjecture has not yet been tested.RAAM networks have been used as an important counter-example to influential analyses of the shortcomings of connectionist cognitive models. The limited success of the RAAM networks in this study brings into question connectionist hopes for an effective RAAM-based cognitive model.

This thesis is concerned with the design of a computer graphics system for in particular artists, and in general surface designers (where surface design refers to the design of 2Dimensional surfaces, e.g. wallpaper, carpets and fabrics). It is argued that the artist tends to be tentative both in terms of plans of action and also the meaning of the image. This is reflected in changes of mind that have consequences on the artists plans and on the structure of the perceived image (i.e. an image perceived in one way may be seen differently later on). On both counts, it is argued, conventional vector based computer graphics does not possess the desired flexibility. Raster graphics employing a 'bitmap' to represent the picture for display offers new potential and greater flexibility. In particular it permits a view of interactive graphics, described as "communicating interpretations" in which the user is seen as being involved in communicating features in a visual scene shared by the man and the machine to the machine. In so doing the user is able to operate on objects in the picture as and when they are perceived. A language (GLIMPS) is described which not only permits the user to generate pictures but also includes facilities for extracting and operating on perceptual features of a picture. GLIMPS makes it possible for both "physical" (region) and "non-physical" (figure on ground) properties of the 'bitmap' to be handled. In conclusion it is argued that the "communicating interpretations" view is more generally applicable in interactive computer graphics.

No description available.

No description available.

No description available.