Spatially Constrained Networks and the Evolution of Modular Control Systems

Fine, Peter; Paolo, Ezequiel A. Di; Philippides, Andrew

doi:10.1007/11840541_45

Cited by 9 publications

(7 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this line of research, a novel graph clustering index called modularity has been proposed recently [1]. The rapidly growing interest in this measure prompted a series of follow-up studies on various applications and possible adjustments (see, e.g., [2], [3], [4], [5], [6]). Moreover, an array of heuristic algorithms has been proposed to optimize modularity.…”

Section: Introductionmentioning

confidence: 99%

On Modularity Clustering

Brandes

Delling

Gaertler

et al. 2008

IEEE Trans. Knowl. Data Eng.

1,080

768

View full text Add to dashboard Cite

Abstract-Modularity is a recently introduced quality measure for graph clusterings. It has immediately received considerable attention in several disciplines, and in particular in the complex systems literature, although its properties are not well understood. We study the problem of finding clusterings with maximum modularity, thus providing theoretical foundations for past and present work based on this measure. More precisely, we prove the conjectured hardness of maximizing modularity both in the general case and with the restriction to cuts, and give an Integer Linear Programming formulation. This is complemented by first insights into the behavior and performance of the commonly applied greedy agglomerative approach.

show abstract

Section: Introductionmentioning

confidence: 99%

On Modularity Clustering

Brandes

Delling

Gaertler

et al. 2008

IEEE Trans. Knowl. Data Eng.

1,080

768

View full text Add to dashboard Cite

show abstract

“…The use of explicit notions of space in neural networks has also been explored in [29] and [108], where the authors note that whilst this approach can promote useful behaviours such as modularity, excessive spatial constraints can limit a learning algorithm's ability to explore behavioural space more generally. Explicit notions of space are also found in various other computational models of biochemical processes.…”

Section: Spatialitymentioning

confidence: 99%

“…This representation counteracts problems with growing complexity and increases modularity. In particular, this enables complex problems to be divided into smaller tasks, which improves the evolution of complex structures [29] and permits the inclusion of indepen [30].…”

Section: Evolving Coupled Artificial Signalling Networkmentioning

confidence: 99%

Biochemical connectionism

et al. 2013

View full text Add to dashboard Cite

In this paper, we discuss computational architectures that are motivated by connectionist patterns that occur in biochemical networks, and speculate about how this biochemical approach to connectionism might complement conventional neural approaches. In particular, we focus on three features of biochemical networks that make them distinct from neural networks: their diverse, complex nodal processes, their emergent organisation, and the dynamical behaviours that result from higher-order, self-modifying processes. We also consider the growing use of evolutionary algorithms in the design of connectionist systems, noting how this enables us to explore a wider range of connectionist architectures, and how the close relationship between biochemical networks and biological evolution can guide us in this endeavour.

show abstract

“…In a recent study on the interaction of spatial embedding and modularity in neural networks, successfully evolved basic and plexus GasNet solutions for the triangle-rectangle discrimination task were analyzed to test whether or not the different spatial embeddings led to differences in the modularity of the networks [28]. This revealed that all of the plexus topologies consisted of one component (i.e., every node was reachable from every other node), whilst 14 (out of 33) of the original GasNet runs produced a best performing controller with at least two network components.…”

Section: Modularitymentioning

confidence: 99%