-
One approach of data-mining for Product Driven Systems
International audience -
Neural network predictive control of a heat exchanger
International audience -
Application of neural network and finite element method for multiscale predic...
International audience -
Hybrid modelling of a sugar boiling process
International audience -
Hybrid modelling of the sucrose cristal growth rate
International audience -
Econometric and Neural Network Analysis of the Labor Productivity and Average...
Some of the forecasting algorithmic techniques presented in this paper were applied by the 3rd author in algorithmic contests in which he participated (some examples of tasks... -
An Augmented Lagrangean Approach for the QoS Constrained Routing Problem
Given a directed graph with capacities on each arc and given a set of commodities, the QoS constrained Routing Problem (QCRP) consists in routing each commodity while... -
Neuro-inspired architectures for nano-circuits
Novel manufacturing techniques, such as nanoscale self-assembly or nanoimprint, allow a cost-efficient way to fabricate high-density crossbar matrices (1012... -
Development of an algorithm for large scale vegetation monitoring
The objective of this study is to develop an algorithm for vegetation monitoring using neural networks. It consists in estimating canopy biophysical variables from the... -
Modelling and simulation of InGaP solar cells under solar concentration: Seri...
International audience -
Continuous space models with neural networks in natural language processing
The purpose of language models is in general to capture and to model regularities of language, thereby capturing morphological, syntactical and distributional... -
Biometry by physiological signals
In general, biometrics aims to identify individuals from their biological characteristics. This practice tends to replace the traditional methods of identity... -
Embedding prior knowledge in the reconstruction of sparse signals : Special c...
The work of this thesis concerns the proposal of algorithms for the integration of prior knowledge in the reconstruction of sparse signals. The purpose is mainly to... -
Neural network spatio-temporal scheduling for reconfigurable heterogeneous ar...
Constant evolution of applications, in terms of complexity or performance needs, makes necessary the development of new architectures. Among all proposed... -
Rapid visual processing in monkeys, humans and machines : a forward-looking view
At the boundary between neuroscience and artificial intelligence, computational neuroscience attempts to understand the tremendous computational capacities of the... -
Evolutionary robotics: influence of selective pressures on the emergence of i...
Evolutionary robotics aim at building machines constantly able to learn new knowledges in a continuous, uncontroled and changing world. This method allowed to... -
Application of multilayer perceptron neural networks for predicting the perme...
International audience -
Fuzzy-MSOM : a new fuzzy clustering approach based on neural network
International audience -
Roughness evaluation of vine leaf by image processing
International audience -
Learning and Explaining Preferences with Neural Networks for Multiple Criteri...
The goal of this Ph.D. work is to improve multiple criteria decision making by the use of " context-dependent " preference models. Such models are more realistic than...
