Search Results for author: Kieran Greer

Found 27 papers, 0 papers with code

Exemplars can Reciprocate Principal Components

no code implementations22 Mar 2021 Kieran Greer

Each tree branches to store subsets of other categories, but the rows in those subsets may also be related.

Clustering

New Ideas for Brain Modelling 7

no code implementations4 Nov 2020 Kieran Greer

The earlier models are still consistent in terms of their proposed functionality, but some of the architecture boundaries have been moved to match them up more closely.

An Entropy Equation for Energy

no code implementations7 Jul 2020 Kieran Greer

The equation is so simplistic and generic that it can offer arguments for completely different domains, where the journey ends with a discussion about global energy properties in physics and beyond.

Clustering

New Ideas for Brain Modelling 6

no code implementations11 May 2020 Kieran Greer

The top-level cognitive layer has been re-designed to model the Cognitive Process Language (CPL) of an earlier paper, by refactoring it into a network structure with a light scheduler.

Chunking Clustering

How the Brain might use Division

no code implementations11 Mar 2020 Kieran Greer

In this paper, the author suggests that the maths question can be answered more easily if the problem is changed into one of symbol manipulation and not just number counting.

Image Recognition using Region Creep

no code implementations24 Sep 2019 Kieran Greer

These areas can overlap with each other and when moving from a region to its neighbours, there is likely to be only small changes in the area image part.

Image Classification

A Pattern-Hierarchy Classifier for Reduced Teaching

no code implementations16 Apr 2019 Kieran Greer

Lower-level pattern ensembles are learned in an unsupervsised manner and then split into branches when it is clear that the category has changed.

Clustering

A Concept-Value Network as a Brain Model

no code implementations9 Apr 2019 Kieran Greer

The paper suggests that features are in fact the wiring.

Category Trees

no code implementations6 Nov 2018 Kieran Greer

Each category is represented by a classifier, where each classifier classifies its own subset of data rows, using batch input values to represent the centroid.

New Ideas for Brain Modelling 5

no code implementations5 Mar 2018 Kieran Greer

It is based on the functionality that a human brain might have, which is a highly distributed network of simple neuronal components that can apply some level of matching and cross-referencing over retrieved patterns.

An Improved Oscillating-Error Classifier with Branching

no code implementations19 Nov 2017 Kieran Greer

This paper extends the earlier work on an oscillating error correction technique.

New Ideas for Brain Modelling 4

no code implementations16 Aug 2017 Kieran Greer

For image processing, a grid-like structure is used with 'full linking'.

New Ideas for Brain Modelling 3

no code implementations22 Nov 2016 Kieran Greer

This paper considers a process for the creation and subsequent firing of sequences of neuronal patterns, as might be found in the human brain.

Clustering

Adding Context to Concept Trees

no code implementations17 Jun 2016 Kieran Greer

A Concept Tree is a structure for storing knowledge where the trees are stored in a database called a Concept Base.

A Repeated Signal Difference for Recognising Patterns

no code implementations18 Apr 2016 Kieran Greer

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.

A Brain-like Cognitive Process with Shared Methods

no code implementations17 Jul 2015 Kieran Greer

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.

Clustering

A New Oscillating-Error Technique for Classifiers

no code implementations20 May 2015 Kieran Greer

This paper describes a new method for reducing the error in a classifier.

A More Human Way to Play Computer Chess

no code implementations14 Mar 2015 Kieran Greer

This has completed the theory of an earlier paper and resulted in a more human-like approach to searching for a chess move.

A Single-Pass Classifier for Categorical Data

no code implementations9 Mar 2015 Kieran Greer

This paper describes a new method for classifying a dataset that partitions elements into their categories.

New Ideas for Brain Modelling 2

no code implementations23 Aug 2014 Kieran Greer

This paper describes a relatively simple way of allowing a brain model to self-organise its concept patterns through nested structures.

Arguments for Nested Patterns in Neural Ensembles

no code implementations25 Mar 2014 Kieran Greer

This paper describes a relatively simple way of allowing a brain model to self-organise its concept patterns through nested structures.

Turing: Then, Now and Still Key

no code implementations11 Mar 2014 Kieran Greer

This paper looks at Turing's postulations about Artificial Intelligence in his paper 'Computing Machinery and Intelligence', published in 1950.

Artificial Neuron Modelling Based on Wave Shape

no code implementations5 Mar 2014 Kieran Greer

This paper describes a new model for an artificial neural network processing unit or neuron.

Is Intelligence Artificial?

no code implementations5 Mar 2014 Kieran Greer

This paper agrees that intelligence is a pro-active event, but also notes a second aspect to it that is in the background and mechanical.

New Ideas for Brain Modelling

no code implementations5 Mar 2014 Kieran Greer

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.

Clustering Concept Chains from Ordered Data without Path Descriptions

no code implementations4 Mar 2014 Kieran Greer

Key to this is a count for both the concept itself and also the group or chain that it belongs to.

Clustering

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

no code implementations4 Mar 2014 Kieran Greer

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.

Position

Cannot find the paper you are looking for? You can Submit a new open access paper.