In this paper, we introduce a novel online heuristic for dynamic topological vector quantization models, called SAND (Stable Adaptive Network Drift-handling).This algorithm enhances existing models by enabling them to track non-stationary distributions, i.e., input streams composed of distinct contexts that drift over time.It employs an online out-of-distribution detector to identify context switches and subsequently updates the labels of vector quantization model nodes accordingly.The proposed algorithm is fully unsupervised, requiring no external labels to learn, recall, or adapt to varying contexts.SAND thus provides an efficient solution to continuously learn representations of evolving data streams in dynamic environments.

In this paper, an adaptation of the k-means algorithm and related methods to non-Euclidian topology is presented.The paper introduces a rationale for approximating the geodesics of that topology, as well as a learning rule that is robust to noise.The first results on artificial but very noisy distributions presented here are promising for further experimentation on real cases.19

In this paper, dynamic neural fields (DNFs) are used to develop key features of a cortically-inspired computational module. Under the perspective of designing computational systems that can exhibit the flexibility and genericity of the cortical substrate, using neural field as the competition layer for self-organising modules has to be considered. However, despite the fact that they serve as a biologically-inspired model, applying DNFs to drive self-organisation is not straightforward. In order to address that issue, an original method for evaluating neural field equations is proposed, based on statistical measurements of the field behaviour in some scenarios. Limitations of classical neural field equations are then quantified, and an original field equation is proposed to overcome these difficulties. The performance of the proposed field model is discussed in comparison with some previously considered models, leading to the promotion of the proposed model as a suitable mean for processing competition in cortex-like computation for cognitive systems.

This paper focuses on the possibility of enabling vector quantization learning techniques into dynamic neural fields, as an attempt to enrich their usage in bio-inspired applications. As mathematical approaches prove rather difficult to propose a practical solution, due to the non-linear character of the field equations, we adopt adifferent perspective in order to deal with this problem. This consists in simulating the evolution of the field and design an empirical method able to measure its quality. The developed benchmark framework implementing this approach is used to check whether a given field is capable to behave as expected in various situations, in particular those involving self-organization by vector quantization.

This paper presents a computational model inspired from the cortex organization that defines coherent learning in multiple cortical maps, in order to perform multi-modal coordination. The joint self-organization of the maps is described as a process allowing dealing with multi-modal information within cooperative distributed modules. The very purpose of this approach is the design of a generic distributed architecture for robotic servo-control from a functional view of the cortical information processing.

We present a cortically-inspired self-organizing model designed to deal with sensory-motor applications, and very first experimental results. This model contains several maps and produces resonance effects between these maps in order to reach an organization compromise.

This paper presents a model of cooperation between representations of correlation in the associative cortex and goal oriented representations of action in the prefrontal cortex. The model is applied to robot navigation and gives a framework for addressing planning with numerical neural techniques.