Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 0705.2307

A Study in a Hybrid Centralised-Swarm Agent Community

Bradley van Aardt·Tshilidzi Marwala
View original source ↗Read source document ↗Export metadata ↓

Abstract

This paper describes a systems architecture for a hybrid Centralised/Swarm based multi-agent system. The issue of local goal assignment for agents is investigated through the use of a global agent which teaches the agents responses to given situations. We implement a test problem in the form of a Pursuit game, where the Multi-Agent system is a set of captor agents. The agents learn solutions to certain board positions from the global agent if they are unable to find a solution. The captor agents learn through the use of multi-layer perceptron neural networks. The global agent is able to solve board positions through the use of a Genetic Algorithm. The cooperation between agents and the results of the simulation are discussed here. .

Explore related subjects

cs.NEcs.AI

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Bradley van Aardt, Tshilidzi Marwala. 2007-05-16. A Study in a Hybrid Centralised-Swarm Agent Community. https://arxiv.org/abs/0705.2307

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

On Orthogonal Recurrent Neural Networks Quantization

In recent years, Orthogonal Recurrent Neural Networks (ORNNs) have gained popularity due to their ability to manage tasks involving long-term dependencies, such as the Copy-task, and their linear complexity. However, existing ORNNs utilize full precision weights and activations, which prevents their deployment on compact devices. In this paper, we explore the quantization of the weight matrices in ORNNs, leading to Quantized approximately Orthogonal RNNs (QORNNs). The construction of such networks remained an open problem, acknowledged for its inherent instability. We propose and investigate two strategies to learn QORNN by combining quantization-aware training (QAT) and orthogonal projections. We also study post-training quantization of the activations for pure integer computation of the recurrent loop. The most efficient fully-quantized models are currently the only alternatives for solving the Copy-task with 1000 timesteps. They also surpass existing quantized models on tasks requiring long-term dependencies, such as permuted MNIST as well as some Internet of Things (IoT) tasks. However, they are less effective on tasks where long short-term memory (LSTMs) and other gated RNNs outperform ORNNs.

cs.NE↗
arXiv2026

Isotropic Activation Functions Enable Deindividuated Neurons and Adaptive Topologies

Varying the number of neurons while preserving function is difficult because neural networks' dense connectivity creates strong computational interdependence between units. Elementwise activation functions, particularly their limited equivariance properties, are identified as a central hurdle to achieving this. We propose activation functions designed around chosen equivariances, enabling dense neural networks to adapt via singular value decomposition of their affine maps. This diagonalises layers into one-to-one, ordered connections, making it easier to assess the impact of individual connections on function. Low-impact neurons can be removed (neurodegeneration), and a thresholded buffer of largely inactive `scaffold' neurons is maintained (neurogenesis). These symmetry-led diagonalisation and structural changes prioritise function-invariance: neurogenesis exactly preserves function, neurodegeneration is asymptotically function-preserving with the pruned singular-value threshold. Moreover, this construction enables asymptotic 50\% parameter sparsification of dense networks while preserving function analytically. Thus, the approach enables real-time restructuring of the architecture in response to task demands, task appending, removal or changes. Conceptually, this motivates broader applications of symmetry prescriptions at the small scale, even when no data-driven model-scale symmetry adherence is required. Following this, we build activations around symmetry, not from classical assumptions about individual neurons. Unlike typical elementwise forms, these alternatives feature explicit basis independence and do not individuate neurons. We leverage this to decompose and reinterpret neurons across sequential layers, simplifying structure and providing a natural route to adaptive topologies. Additional developments include a new tunable parameter, the `intrinsic length'.

cs.NE↗
arXiv2026

Frame Theoretical Derivation of Three Factor Learning Rule for Oja's Subspace Rule

We show that the error-gated Hebbian rule for PCA (EGHR-PCA), a three-factor learning rule equivalent to Oja's subspace rule under Gaussian inputs, can be systematically derived from Oja's subspace rule using frame theory. The global third factor in EGHR-PCA arises exactly as a frame coefficient when the learning rule is expanded with respect to a natural frame on the space of symmetric matrices. This provides a principled, non-heuristic derivation of a biologically plausible learning rule from its mathematically canonical counterpart.

cs.NE↗