Academic, passionate about using neural modelling to check hypotheses about being conscious. Currently working on biological models of various forms of memory, cognitive phenomenology and the history of the the philosophy of mind.
ABSTRACT Visual deficits have been discovered in sufferers of Parkinson’ disease [1] and the caus... more ABSTRACT Visual deficits have been discovered in sufferers of Parkinson’ disease [1] and the cause of this is not clearly understood. This paper reports on a digital neuromodel that investigates a hypothesis that the deficit may be due to a projection from the Basal Ganglia to the Superior Colliculus where a shortage of Dopamine introduces noise in the oculo-motor loop. New experiments were done with Parkinson’s patients to track the deficit and the neuromodel predicts performance against oculo-motor noise. It is seen that a group Parkinson’s sufferers in whom the deficit is pronounced follow the predicted law, while controls with poor performance do not follow the law. This helps to uphold the noise hypothesis.
The European Symposium on Artificial Neural Networks, 2014
ABSTRACT A weightless neural state machine acting as an exploratory automaton changes its positio... more ABSTRACT A weightless neural state machine acting as an exploratory automaton changes its position in a simulated toy world by its own actions. A popular question is asked: how might the automaton ‘become conscious of’ the effect of its own actions? Here we develop previously defined iconic learning in such weightless machines so that this knowledge can be achieved. Weightlessness, iconic learning are expressed in terms of state equations. Experimental results that show the conditions under which correct predictions can be obtained on a neural simulator are presented. Issues of information integration and memory implication are briefly considered at the end of the paper.
Three key points are made in this paper. The first is that “iconic” states arise naturally in all... more Three key points are made in this paper. The first is that “iconic” states arise naturally in all recursive neural nets which are trained on world states. The second point is that this leads to a new paradigm of cognitive representation. Language is seen as a vehicle for retrieving iconic representations in a recursive system — this is dubbed the “iconic hypothesis”. The third point is that while a similar idea has been presented as a “symbol grounding problem” (Harnad, 1990) the “iconic hypothesis” goes further in suggesting that a recursive neural system can operate in both a symbolic fashion and use grounded internal states. To illustrate these points we introduce an architectural concept (the Neural State Machine Model — NSMM) which allows a clear formalisation of the concept of iconic representations. Examples of the application of this concept to representation of visuo-linguistic data are given.
The key element presented in this paper is an adaptive state machine in which neurons form the st... more The key element presented in this paper is an adaptive state machine in which neurons form the state variables and these are sufficient in number for the state to be “iconic”. That is, the state reflects events in the world in a many-to-some manner. Early processing forms part of this model. The model is a variant of the previously defined Neural State Machine Model (NSMM). The variant presented in this paper has the ability of functioning in the vision domain both in a rule-based way and an adaptive, neural way. Examples are given of integrated models of concept binding, learning concepts from widely different objects and the memory of scenarios. This is a brief summary of a wide-ranging group of research topics in visual understanding that are enabled by the NSMM technique.
The European Symposium on Artificial Neural Networks, 2019
These are Christof Koch’s [1] closing remarks at the 2001 Swartz Foundation workshop on Machine C... more These are Christof Koch’s [1] closing remarks at the 2001 Swartz Foundation workshop on Machine Consciousness, Cold Spring Harbour Laboratories: “... we know of no fundamental law or principle operating in this universe that forbids the existence of subjective feelings in artefacts designed or evolved by humans.” This account is aimed at identifying a formal expression of the ‘subjective feelings in artefacts’ that Koch saw as being central to the definition of a conscious machine. It is useful to elaborate ‘artefacts’ as the set of systems that have a physically realizable character and an analytic description. The weightless character of the description dispels the notion that cognition and consciousness lurk within the weight values of a system.
International Journal of Machine Consciousness, Jun 1, 2014
ABSTRACT Five reviewers have kindly read our \Aristotle's Laptop: Discovering our Informa... more ABSTRACT Five reviewers have kindly read our \Aristotle's Laptop: Discovering our Informational Minds." Here, we thank them for spending their time, meet some of their comments and indicate developments which their comments encourage.
... IGOR ALEKSANDER, BARRY DUNMALL, VALENTINA DEL FRATE, Neural Systems Engineering Group Departm... more ... IGOR ALEKSANDER, BARRY DUNMALL, VALENTINA DEL FRATE, Neural Systems Engineering Group Department of Electrical and Electronic Engineering Imperial ... We assume that names of values exist in verbal areas that assume some ordering of names tlwough grammar. ...
How can a system with visual input become capable of visualising what is meant by new combination... more How can a system with visual input become capable of visualising what is meant by new combinations of known words? For example, it is possible for most of us to visualise a blue banana with red spots even though such an object would never have formed part of our experience. The authors discuss a neural system which is capable of
ABSTRACT Visual deficits have been discovered in sufferers of Parkinson’ disease [1] and the caus... more ABSTRACT Visual deficits have been discovered in sufferers of Parkinson’ disease [1] and the cause of this is not clearly understood. This paper reports on a digital neuromodel that investigates a hypothesis that the deficit may be due to a projection from the Basal Ganglia to the Superior Colliculus where a shortage of Dopamine introduces noise in the oculo-motor loop. New experiments were done with Parkinson’s patients to track the deficit and the neuromodel predicts performance against oculo-motor noise. It is seen that a group Parkinson’s sufferers in whom the deficit is pronounced follow the predicted law, while controls with poor performance do not follow the law. This helps to uphold the noise hypothesis.
The European Symposium on Artificial Neural Networks, 2014
ABSTRACT A weightless neural state machine acting as an exploratory automaton changes its positio... more ABSTRACT A weightless neural state machine acting as an exploratory automaton changes its position in a simulated toy world by its own actions. A popular question is asked: how might the automaton ‘become conscious of’ the effect of its own actions? Here we develop previously defined iconic learning in such weightless machines so that this knowledge can be achieved. Weightlessness, iconic learning are expressed in terms of state equations. Experimental results that show the conditions under which correct predictions can be obtained on a neural simulator are presented. Issues of information integration and memory implication are briefly considered at the end of the paper.
Three key points are made in this paper. The first is that “iconic” states arise naturally in all... more Three key points are made in this paper. The first is that “iconic” states arise naturally in all recursive neural nets which are trained on world states. The second point is that this leads to a new paradigm of cognitive representation. Language is seen as a vehicle for retrieving iconic representations in a recursive system — this is dubbed the “iconic hypothesis”. The third point is that while a similar idea has been presented as a “symbol grounding problem” (Harnad, 1990) the “iconic hypothesis” goes further in suggesting that a recursive neural system can operate in both a symbolic fashion and use grounded internal states. To illustrate these points we introduce an architectural concept (the Neural State Machine Model — NSMM) which allows a clear formalisation of the concept of iconic representations. Examples of the application of this concept to representation of visuo-linguistic data are given.
The key element presented in this paper is an adaptive state machine in which neurons form the st... more The key element presented in this paper is an adaptive state machine in which neurons form the state variables and these are sufficient in number for the state to be “iconic”. That is, the state reflects events in the world in a many-to-some manner. Early processing forms part of this model. The model is a variant of the previously defined Neural State Machine Model (NSMM). The variant presented in this paper has the ability of functioning in the vision domain both in a rule-based way and an adaptive, neural way. Examples are given of integrated models of concept binding, learning concepts from widely different objects and the memory of scenarios. This is a brief summary of a wide-ranging group of research topics in visual understanding that are enabled by the NSMM technique.
The European Symposium on Artificial Neural Networks, 2019
These are Christof Koch’s [1] closing remarks at the 2001 Swartz Foundation workshop on Machine C... more These are Christof Koch’s [1] closing remarks at the 2001 Swartz Foundation workshop on Machine Consciousness, Cold Spring Harbour Laboratories: “... we know of no fundamental law or principle operating in this universe that forbids the existence of subjective feelings in artefacts designed or evolved by humans.” This account is aimed at identifying a formal expression of the ‘subjective feelings in artefacts’ that Koch saw as being central to the definition of a conscious machine. It is useful to elaborate ‘artefacts’ as the set of systems that have a physically realizable character and an analytic description. The weightless character of the description dispels the notion that cognition and consciousness lurk within the weight values of a system.
International Journal of Machine Consciousness, Jun 1, 2014
ABSTRACT Five reviewers have kindly read our \Aristotle's Laptop: Discovering our Informa... more ABSTRACT Five reviewers have kindly read our \Aristotle's Laptop: Discovering our Informational Minds." Here, we thank them for spending their time, meet some of their comments and indicate developments which their comments encourage.
... IGOR ALEKSANDER, BARRY DUNMALL, VALENTINA DEL FRATE, Neural Systems Engineering Group Departm... more ... IGOR ALEKSANDER, BARRY DUNMALL, VALENTINA DEL FRATE, Neural Systems Engineering Group Department of Electrical and Electronic Engineering Imperial ... We assume that names of values exist in verbal areas that assume some ordering of names tlwough grammar. ...
How can a system with visual input become capable of visualising what is meant by new combination... more How can a system with visual input become capable of visualising what is meant by new combinations of known words? For example, it is possible for most of us to visualise a blue banana with red spots even though such an object would never have formed part of our experience. The authors discuss a neural system which is capable of
Uploads
Papers by Igor Aleksander