arXiv subjects

Kieran Greer

Publications and source records attributed to Kieran Greer.

34 records · Page 2Linked to original sources

arXiv2017

A Brain-like Cognitive Process with Shared Methods

This paper describes a new entropy-style of equation that may be useful in a general sense, but can be applied to a cognitive model with related processes. The model is based on the human brain, with automatic and distributed pattern activity. Methods for carrying out the different processes are suggested. The main purpose of this paper is to reaffirm earlier research on different knowledge-based and experience-based clustering techniques. The overall architecture has stayed essentially the same and so it is the localised processes or smaller details that have been updated. For example, a counting mechanism is used slightly differently, to measure a level of 'cohesion' instead of a 'correct' classification, over pattern instances. The introduction of features has further enhanced the architecture and the new entropy-style equation is proposed. While an earlier paper defined three levels of functional requirement, this paper re-defines the levels in a more human vernacular, with higher-level goals described in terms of action-result pairs.

cs.AI↗

arXiv2016

New Ideas for Brain Modelling

This paper describes some biologically-inspired processes that could be used to build the sort of networks that we associate with the human brain. New to this paper, a 'refined' neuron will be proposed. This is a group of neurons that by joining together can produce a more analogue system, but with the same level of control and reliability that a binary neuron would have. With this new structure, it will be possible to think of an essentially binary system in terms of a more variable set of values. The paper also shows how recent research associated with the new model, can be combined with established theories, to produce a more complete picture. The propositions are largely in line with conventional thinking, but possibly with one or two more radical suggestions. An earlier cognitive model can be filled in with more specific details, based on the new research results, where the components appear to fit together almost seamlessly. The intention of the research has been to describe plausible 'mechanical' processes that can produce the appropriate brain structures and mechanisms, but that could be used without the magical 'intelligence' part that is still not fully understood. There are also some important updates from an earlier version of this paper.

cs.AI↗

arXiv2016

A Repeated Signal Difference for Recognising Patterns

This paper describes a new mechanism that might help with defining pattern sequences, by the fact that it can produce an upper bound on the ensemble value that can persistently oscillate with the actual values produced from each pattern. With every firing event, a node also receives an on/off feedback switch. If the node fires, then it sends a feedback result depending on the input signal strength. If the input signal is positive or larger, it can store an 'on' switch feedback for the next iteration. If the signal is negative or smaller, it can store an 'off' switch feedback for the next iteration. If the node does not fire, then it does not affect the current feedback situation and receives the switch command produced by the last active pattern event for the same neuron. The upper bound therefore also represents the largest or most enclosing pattern set and the lower value is for the actual set of firing patterns. If the pattern sequence repeats, it will oscillate between the two values, allowing them to be recognised and measured more easily, over time. Tests show that changing the sequence ordering produces different value sets, which can also be measured.

cs.NE↗

arXiv2016

A Single-Pass Classifier for Categorical Data

This paper describes a new method for classifying a dataset that partitions elements into their categories. It has relations with neural networks but a slightly different structure, requiring only a single pass through the classifier to generate the weight sets. A grid-like structure is required as part of a novel idea of converting a 1-D row of real values into a 2-D structure of value bands. Each cell in any band then stores a distinct set of weights, to represent its own importance and its relation to each output category. During classification, all of the output weight lists can be retrieved and summed to produce a probability for what the correct output category is. The bands possibly work like hidden layers of neurons, but they are variable specific, making the process orthogonal. The construction process can be a single update process without iterations, making it potentially much faster. It can also be compared with k-NN and may be practical for partial or competitive updating.

cs.AI↗

arXiv2014

New Ideas for Brain Modelling 2

This paper describes a relatively simple way of allowing a brain model to self-organise its concept patterns through nested structures. For a simulation, time reduction is helpful and it would be able to show how patterns may form and then fire in sequence, as part of a search or thought process. It uses a very simple equation to show how the inhibitors in particular, can switch off certain areas, to allow other areas to become the prominent ones and thereby define the current brain state. This allows for a small amount of control over what appears to be a chaotic structure inside of the brain. It is attractive because it is still mostly mechanical and therefore can be added as an automatic process, or the modelling of that. The paper also describes how the nested pattern structure can be used as a basic counting mechanism. Another mathematical conclusion provides a basis for maintaining memory or concept patterns. The self-organisation can space itself through automatic processes. This might allow new neurons to be added in a more even manner and could help to maintain the concept integrity. The process might also help with finding memory structures afterwards. This extended version integrates further with the existing cognitive model and provides some new conclusions.

cs.AI↗

arXiv2014

Concept Trees: Building Dynamic Concepts from Semi-Structured Data using Nature-Inspired Methods

This paper describes a method for creating structure from heterogeneous sources, as part of an information database, or more specifically, a 'concept base'. Structures called 'concept trees' can grow from the semi-structured sources when consistent sequences of concepts are presented. They might be considered to be dynamic databases, possibly a variation on the distributed Agent-Based or Cellular Automata models, or even related to Markov models. Semantic comparison of text is required, but the trees can be built more, from automatic knowledge and statistical feedback. This reduced model might also be attractive for security or privacy reasons, as not all of the potential data gets saved. The construction process maintains the key requirement of generality, allowing it to be used as part of a generic framework. The nature of the method also means that some level of optimisation or normalisation of the information will occur. This gives comparisons with databases or knowledge-bases, but a database system would firstly model its environment or datasets and then populate the database with instance values. The concept base deals with a more uncertain environment and therefore cannot fully model it beforehand. The model itself therefore evolves over time. Similar to databases, it also needs a good indexing system, where the construction process provides memory and indexing structures. These allow for more complex concepts to be automatically created, stored and retrieved, possibly as part of a more cognitive model. There are also some arguments, or more abstract ideas, for merging physical-world laws into these automatic processes.

cs.IR↗

arXiv2014

Recent Developments with the licas System 2

The licas (lightweight Internet-based communication for autonomic services) system is a Java-based open source framework for building service-based networks, similar to what you would use a Cloud or SOA platform for. The framework comes with a server for running the services on, mechanisms for adding services to the server, mechanisms for linking services with each other, and mechanisms for allowing the services to communicate with each other. The general architecture of the system is now fairly well set, where this paper describes recent developments that have focused on making the framework more robust and additional features for easier programming.

cs.DC↗

arXiv2014

Arguments for Nested Patterns in Neural Ensembles

This paper describes a relatively simple way of allowing a brain model to self-organise its concept patterns through nested structures. Time is a key element and a simulator would be able to show how patterns may form and then fire in sequence, as part of a search or thought process. It uses a very simple equation to show how the inhibitors in particular, can switch off certain areas, to allow other areas to become the prominent ones and thereby define the current brain state. This allows for a small amount of control over what appears to be a chaotic structure inside of the brain. It is attractive because it is still mostly mechanical and therefore can be added as an automatic process, or the modelling of that. The paper also describes how the nested pattern structure can be used as a basic counting mechanism.

cs.NE↗

arXiv2014

Turing: Then, Now and Still Key

This paper looks at Turing's postulations about Artificial Intelligence in his paper 'Computing Machinery and Intelligence', published in 1950. It notes how accurate they were and how relevant they still are today. This paper notes the arguments and mechanisms that he suggested and tries to expand on them further. The paper however is mostly about describing the essential ingredients for building an intelligent model and the problems related with that. The discussion includes recent work by the author himself, who adds his own thoughts on the matter that come from a purely technical investigation into the problem. These are personal and quite speculative, but provide an interesting insight into the mechanisms that might be used for building an intelligent system.

cs.AI↗

arXiv2014

Artificial Neuron Modelling Based on Wave Shape

This paper describes a new model for an artificial neural network processing unit or neuron. It is slightly different to a traditional feedforward network by the fact that it favours a mechanism of trying to match the wave-like 'shape' of the input with the shape of the output against specific value error corrections. The expectation is then that a best fit shape can be transposed into the desired output values more easily. This allows for notions of reinforcement through resonance and also the construction of synapses.

cs.NE↗

arXiv2014

Recent Developments with the licas System

This paper describes recent developments with the licas (lightweight Internet-based communication for autonomic services) software package. In particular, it describes how the architecture and functionality have changed from the first version release. The autonomous nature of the system is focused on, which requires independent behaviour and metadata descriptions of each service. The system has now also been ported to the Java mobile environment. Then some open questions or problems will be discussed in the areas of metadata consistency, security and trust. Finally, some solutions to these problems will also be suggested.

cs.DC↗

arXiv2014

The Obvious Solution to Semantic Mapping -- Ask an Expert

The semantic mapping problem is probably the main obstacle to computer-to-computer communication. If computer A knows that its concept X is the same as computer B's concept Y, then the two machines can communicate. They will in effect be talking the same language. This paper describes a relatively straightforward way of enhancing the semantic descriptions of Web Service interfaces by using online sources of keyword definitions. Method interface descriptions can be enhanced using these standard dictionary definitions. Because the generated metadata is now standardised, this means that any other computer that has access to the same source, or understands standard language concepts, can now understand the description. This helps to remove a lot of the heterogeneity that would otherwise build up though humans creating their own descriptions independently of each other. The description comes in the form of an XML script that can be retrieved and read through the Web Service interface itself. An additional use for these scripts would be for adding descriptions in different languages, which would mean that human users that speak a different language would also understand what the service was about.

cs.IR↗

arXiv2014

Evaluating Dynamic Linking through the Query Process using the Licas Test Platform

A novel linking mechanism has been described previously [4] that can be used to autonomously link sources that provide related answers to queries executed over an information network. The test query platform has now been re-written resulting in essentially a new test platform using the same basic query mechanism, but with a slightly different algorithm. This paper describes recent test results on the same query test process that supports the original findings and also shows the effectiveness of the linking mechanism in a new set of test scenarios.

cs.DC↗

arXiv2014

Clustering Concept Chains from Ordered Data without Path Descriptions

This paper describes a process for clustering concepts into chains from data presented randomly to an evaluating system. There are a number of rules or guidelines that help the system to determine more accurately what concepts belong to a particular chain and what ones do not, but it should be possible to write these in a generic way. This mechanism also uses a flat structure without any hierarchical path information, where the link between two concepts is made at the level of the concept itself. It does not require related metadata, but instead, a simple counting mechanism is used. Key to this is a count for both the concept itself and also the group or chain that it belongs to. To test the possible success of the mechanism, concept chain parts taken randomly from a larger ontology were presented to the system, but only at a depth of 2 concepts each time. That is - root concept plus a concept that it is linked to. The results show that this can still lead to very variable structures being formed and can also accommodate some level of randomness.

cs.AI↗

arXiv2014

A Metric for Modelling and Measuring Complex Behavioural Systems

This paper describes a metric for measuring the success of a complex system composed of agents performing autonomous behaviours. Because of the difficulty in evaluating such systems, this metric will help to give an initial indication as to how suitable the agents would be for solving the problem. The system is modelled as a script, or behavioural ontology, with a number of variables to represent each of the behaviour attributes. The set of equations can be used both for modeling and as part of the simulation evaluation. Behaviours can be nested, allowing for compound behaviours of arbitrary complexity to be built. There is also the capability for including rules or decision making into the script. The paper also gives some test examples to show how the metric might be used.

cs.MA↗

arXiv2014

Dynamic Move Chains -- a Forward Pruning Approach to Tree Search in Computer Chess

This paper proposes a new mechanism for pruning a search game-tree in computer chess. The algorithm stores and then reuses chains or sequences of moves, built up from previous searches. These move sequences have a built-in forward-pruning mechanism that can radically reduce the search space. A typical search process might retrieve a move from a Transposition Table, where the decision of what move to retrieve would be based on the position itself. This algorithm stores move sequences based on what previous sequences were better, or caused cutoffs. This is therefore position independent and so it could also be useful in games with imperfect information or uncertainty, where the whole situation is not known at any one time. Over a small set of tests, the algorithm was shown to clearly out-perform Transposition Tables, both in terms of search reduction and game-play results.

cs.AI↗