Biomedical subjects

Igor Aleksander

Publications and source records attributed to Igor Aleksander.

3 recordsLinked to original sources

PubMed2005

Machine consciousness.

The work from several laboratories on the modeling of consciousness is reviewed. This ranges, on one hand, from purely functional models where behavior is important and leads to an attribution of consciousness to, on the other hand, material work closely derived from the information about the anatomy of the brain. At the functional end of the spectrum, applications are described specifically directed at a job-finding problem, where the person being served should not discern between being served by a conscious human or a machine. This employs an implementation of global workspace theories. At the material end, attempts at modeling attentional brain mechanisms, and basic biochemical processes in children are discussed. There are also general prescriptions for functional schemas that facilitate discussions for the presence of consciousness in computational systems and axiomatic structures that define necessary architectural features without which it would be difficult to represent sensations. Another distinction between these two approaches is whether one attempts to model phenomenology (material end) or not (functional end). The former is sometimes called "synthetic phenomenology." The upshot of this chapter is that studying consciousness through the design of machines is likely to have two major outcomes. The first is to provide a wide-ranging computational language to express the concept of consciousness. The second is to suggest a wide-ranging set of computational methods for building competent machinery that benefits from the flexibility of conscious representations.

Consciousness↗

PubMed2003

Predicting the behaviour of G-RAM networks.

A Generalising Random Access Memory (G-RAM) neuron is distinguished from conventional neuron models by the fact that its tolerance to departures in similarity from its training pattern is variable. Details of this are given in this paper as it affects the behaviour a class of digital probabilistic neural networks which have been achieving attention in the neural networks literature for some years now. Such systems are also called n-tuple systems, weightless systems or p-RAM systems. After reviewing the literature on such networks, a novel simple combinatoric analysis of the most likely behaviour of recursive GRAM networks is described. The best network performance, measured by a key parameter called 'radius of retrievability' (first defined by Wong and Sherrington [J. Phys. A 22 (1989) 2233] as the error in the input that still allows evolution of the dynamic network to the correct attractor state), is obtained with a training set composed of random data patterns. Increasing the size of the training set reduces this radius of retrievability in a predictable manner. Changing the nature of the training set to non-random patterns also reduces the radius of retrievability to an extent that we show can be estimated from a measure of the diversity of the elements of the training set (we refer to this as the 'mean intra-set Hamming distance of the training set'). As mentioned earlier the feature of G-RAMs (indicated by the G) is that there exists a generalization parameter which determines how far a neuron input vector can stray from a training input for the neuron to respond in the trained way. It is shown that when this generalization parameter is reduced, then the radius of retrievability is also reduced but it is then stable in the face of an increase in size, or change in nature, of the training set. This is a novel prediction of the behaviour of systems and of the robustness of such behaviour in the face of varying the size and correlation properties of the training set.

Algorithms↗

PubMed1997

Consciousness and neural cognizers: a review of some recent approaches.

This paper synthesises three diverse approaches to the study of consciousness in a description of an existing program of work in Artificial Neuroconsciousness. The three approaches are drawn from automata theory ([Aleksander, 1995][Aleksander, 1996]), psychology ([Karmiloff-Smith, 1992]; [Clark Karmiloff-Smith, 1993]) and philosophy ([Searle, 1992]).Previous work on bottom-level sensory-motor tasks from the program is described as a background to the current work on generating higher-level, abstract concepts which are an essential part of mental life. The entire program of work postulates automata theory as an appropriate framework for the study of cognition. It is demonstrated how both the bottom-level sensory-motor tasks and abstract knowledge representations can be tackled by a single neural state machine architecture. The resulting state space representations are then reconciled with both the psychological and philosophical theories, suggesting the appropriateness of taking an automata theory approach to consciousness.

Journal Article↗