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.

Auto-associative memory using n-tuple techniques

The use of n-tuple or weightless neural networks as pattern recognition devices has been well documented. They have a significant advantages over more common networks paradigms, such as the multilayer perceptron in that they can be easily implemented in digital hardware using standard random access memories. To date, n-tuple networks have predominantly been used as fast pattern classification devices. The paper describes how n-tuple techniques can be used in the hardware implementation of a general auto-associative network.

A Wiener model for memory high power amplifiers using B-spline function approximation

In this paper we introduce a new Wiener system modeling approach for memory high power amplifiers in communication systems using observational input/output data. By assuming that the nonlinearity in the Wiener model is mainly dependent on the input signal amplitude, the complex valued nonlinear static function is represented by two real valued B-spline curves, one for the amplitude distortion and another for the phase shift, respectively. The Gauss-Newton algorithm is applied for the parameter estimation, which incorporates the De Boor algorithm, including both the B-spline curve and the first order derivatives recursion. An illustrative example is utilized to demonstrate the efficacy of the proposed approach.

Self-centred memories: the reminiscence bump and the self

The self-memory relationship is thought to be bidirectional, in such a way that memories provide context for the self, and equally, the self exercises control over retrieval (Conway, 2005). Autobiographical memories are not distributed equally across the life span; instead, memories peak between ages 10 and 30. This reminiscence bump has been suggested to support the emergence of a stable and enduring self. In the present study, the relationship between memory accessibility and self was explored with a novel methodology that used generation of self images in the form of I am statements. Memories generated from I am cues clustered around the time of emergence for that particular self image. We argue that, when a new self-image is formed, it is associated with the encoding of memories that are relevant to that self and that remain highly accessible to the rememberer later in life. This study offers a new methodology for academics and clinicians interested in the relationship between memory and identity.

‘Souvenirs, souvenirs': the role of memory in the work of Annie Saumont

The work of nouvelliste Annie Saumont constantly explores the phenomenon of memory, and of memories. This article identifies and nuances the various forms that this exploration takes. An introductory contextualization of author and theme is followed by the presentation of a short story, ‘Méandres’, which embodies the first quality of memory to be examined: its capacity not only to recall but also to re-evaluate a past which is thus shown to be as hypothetical as the future. Memory as guilt that moulds or puts its indelible stamp on lives is then evoked by means of examples from other stories, illustrating the gradations Saumont achieves in her investigation of the power of this complex faculty. The next section turns to her portrayal of involuntary memory. Unlike for Proust, the instances of spontaneous remembering that are experienced by her characters lunge at them down the years almost exclusively to wound or disorientate. Depictions of the memory which conserves, and is thus burdened by, secrets are then considered, and finally Saumont's evocation of characters who have different reasons to analyse the way their own and other people's memories work. The conclusion to be drawn is that for Saumont, we are our memories; the ability to master a ‘judicious interpretation’ of memory – or indeed, to forget – is, in her stories, overwhelmingly a quality to be envied.