M
Matthew Poole
Researcher at University of Portsmouth
Publications - 20
Citations - 370
Matthew Poole is an academic researcher from University of Portsmouth. The author has contributed to research in topics: Particle swarm optimization & Swarm intelligence. The author has an hindex of 10, co-authored 20 publications receiving 338 citations. Previous affiliations of Matthew Poole include Swansea University & University of Leeds.
Papers
More filters
Journal ArticleDOI
Coupling CMLs and the synchronization of a multilayer neural computing system
TL;DR: This work analyzes a general process to realize a multilayer structured CML by coupling m CMLs together with arbitrary coupling structure and uses this coupling process in the study of a CML with multilayers planar architecture and non-symmetric hierarchical coupling between the layers.
Book ChapterDOI
Hierarchies of Spatially Extended Systems and Synchronous Concurrent Algorithms
TL;DR: The computability and the equational definability of SESs are examined and it is shown that, in the discrete case, there is a natural sense in which an SES is computable if, and only if, it is definable by equations.
Book ChapterDOI
Incorporating Heuristics in a Swarm Intelligence Framework for Inferring Gene Regulatory Networks from Gene Expression Time Series
TL;DR: This paper implements an ant system to generate candidate network structures using a particle swarm optimization algorithm, and extends this approach by incorporating domain-specific heuristics to the ant system, as a mechanism that has the potential to bias the pheromone amplification effect towards biologically plausible relationships.
Proceedings ArticleDOI
Extending the design of a blocks-based python environment to support complex types
TL;DR: The design of PyBlocks is extended to include Python's most common built-in composite types (lists, tuples, dictionaries and sets) and to allow nesting of these where appropriate and to show how further types may be supported.
Proceedings ArticleDOI
Design of a blocks-based environment for introductory programming in Python
TL;DR: The design promotes understanding of how data types are used in the language by representing them using colors: each expression block is colored according to its type, and each unfilled hole contains colors which indicate valid argument types.