Optimising memory usage in n-tuple neural networks

The use of n-tuple or weightless neural networks as pattern recognition devices is well known (Aleksander and Stonham, 1979). They have some significant advantages over the more common and biologically plausible networks, such as multi-layer perceptrons; for example, n-tuple networks have been used for a variety of tasks, the most popular being real-time pattern recognition, and they can be implemented easily in hardware as they use standard random access memories. In operation, a series of images of an object are shown to the network, each being processed suitably and effectively stored in a memory called a discriminator. Then, when another image is shown to the system, it is processed in a similar manner and the system reports whether it recognises the image; is the image sufficiently similar to one already taught? If the system is to be able to recognise and discriminate between m-objects, then it must contain m-discriminators. This can require a great deal of memory. This paper describes various ways in which memory requirements can be reduced, including a novel method for multiple discriminator n-tuple networks used for pattern recognition. By using this method, the memory normally required to handle m-objects can be used to recognise and discriminate between 2^m — 2 objects.

The ecology of crusading: investigating the environmental impact of holy war and colonisation at the frontiers of medieval Europe

The Crusades in the Near East, eastern Baltic and Iberian Peninsula (in the context of the Reconquest/reconquista) were accompanied by processes of colonisation, characterising the expansion of medieval Europe and resulting in the creation of frontier societies at the fringes of Christendom. Colonisation was closely associated with — indeed, depended on — the exploitation of local environments, but this dimension is largely missing from studies of the crusading frontiers. This paper, the product of a European Science Foundation Exploratory Workshop on 'The Ecology of Crusading' in 2009, surveys the potential for investigating the environmental impact of the crusading movement in all three frontier regions. It considers a diverse range of archaeological, palaeoenvironmental and written sources, with the aim of situating the societies created by the Crusades within the context of medieval colonisation and human ecological niche construction. It demonstrates that an abundant range of data exists for developing this largely neglected and disparately studied aspect of medieval frontier societies into a significant research programme.

Non-visual and multisensory BCI systems: present and future

During the past decade, brain–computer interfaces (BCIs) have rapidly developed, both in technological and application domains. However, most of these interfaces rely on the visual modality. Only some research groups have been studying non-visual BCIs, primarily based on auditory and, sometimes, on somatosensory signals. These non-visual BCI approaches are especially useful for severely disabled patients with poor vision. From a broader perspective, multisensory BCIs may offer more versatile and user-friendly paradigms for control and feedback. This chapter describes current systems that are used within auditory and somatosensory BCI research. Four categories of noninvasive BCI paradigms are employed: (1) P300 evoked potentials, (2) steady-state evoked potentials, (3) slow cortical potentials, and (4) mental tasks. Comparing visual and non-visual BCIs, we propose and discuss different possible multisensory combinations, as well as their pros and cons. We conclude by discussing potential future research directions of multisensory BCIs and related research questions