Jean-Pierre Mano

Mimicking human neuronal pathways in silico: an emergent model on the effective connectivity

We present a novel computational model that detects temporal configurations of a given human neuronal pathway and constructs its artificial replication. This poses a great challenge since direct recordings from individual neurons are impossible in the human central nervous system and therefore the underlying neuronal pathway has to be considered as a black box. For tackling this challenge, we used a branch of complex systems modeling called artificial self-organization in which large sets of software entities interacting locally give rise to bottom-up collective behaviors. The result is an emergent model where each software entity represents an integrate-and-fire neuron. We then applied the model to the reflex responses of single motor units obtained from conscious human subjects. Experimental results show that the model recovers functionality of real human neuronal pathways by comparing it to appropriate surrogate data. What makes the model promising is the fact that, to the best of our knowledge, it is the first realistic model to self-wire an artificial neuronal network by efficiently combining neuroscience with artificial self-organization. Although there is no evidence yet of the model’s connectivity mapping onto the human connectivity, we anticipate this model will help neuroscientists to learn much more about human neuronal networks, and could also be used for predicting hypotheses to lead future experiments.

Simulating Human Single Motor Units Using Self-Organizing Agents

Understanding functional synaptic connectivity of human central nervous system is one of the holy grails of the neuroscience. Due to the complexity of nervous system, it is common to reduce the problem to smaller networks such as motor unit pathways. In this sense, we designed and developed a simulation model that learns acting in the same way of human single motor units by using findings on human subjects. The developed model is based on self-organizing agents whose nominal and cooperative behaviors are based on the current knowledge on biological neural networks. The results show that the simulation model generates similar functionality with the observed data.

Adaptive Multi-agent System for Multi-sensor Maritime Surveillance

Maritime surveillance is a difficult task as its aim is to detect any threatening event in a dynamic, complex and hugely distributed system. As there are many different types of vessels, behaviours, situations, and because the system is constantly evolving, classical automated surveillance approaches are unrealistic. We propose an adaptive multi-agent system in which each agent is responsible for a vessel. This agent perceives local anomalies and combines them to maintain a criticality value, used to decide when an alert is appropriate. The importance of the anomalies and how they are combined emerges from a cooperative selfadjusting process taking user feedback into account. This software is currently under development in ScanMaris, a project supported by the French National Research Agency.

Property analysis of open networks of cooperative neuro-agents using AMAS theory

According to the most recent research on adaptive multi-agent systems, it is possible to assess that those systems are able of building by themselves a representation of their surrounding world. Using cooperation as a local criterion of self-organization it become possible to make a multi-agent system learn how to interpret the different signals it receives in order to adapt its functioning to its environment. After an adaptation period, a complex system is able to emerge by the way of a self-organized learning network.

MAS4AT : un SMA auto-adaptatif pour le déclenchement d'alertes dans le cadre de la surveillance maritime

Cet article presente MAS4AT, un systeme multi-agent cooperatif et auto-adaptatif pour le declenchement d’alertes lors de la detection de comportements suspects dans le cadre de la surveillance maritime. Ce systeme est concu et developpe dans le cadre du projet europeen I2C qui vise a mettre en œuvre une nouvelle generation de systemes de surveillance maritime, capables d’aider les operateurs humains (i) a identifier les comportements anormaux de navires, (ii) a evaluer la suspicion associee a ces comportements et (iii) a declencher des alertes s’ils representent des menaces. Cet article introduit le projet I2C puis se consacre plus particulierement a la presentation de MAS4AT et a ses capacites d’apprentissage par renforcement.

Agent-Based Model for Phenotypic Prediction Using Genomic and Environmental Data

One of the means to increase in-field crop yields is the use of software tools to predict future yield values using past in-field trials and plant genetics. The traditional, statistics-based approaches lack environmental data integration and are very sensitive to missing and/or noisy data. In this paper, we show how using a cooperative, adaptive Multi-Agent System can overcome the drawbacks of such algorithms. The system resolves the problem in an iterative way by a cooperation between the constraints, modelled as agents. Results show a good convergence of the algorithm. Complete tests to validate the provided solution quality are still in progress.