Conducted for the Treasury Board of Québec, this study seeks to present recent contributions to the evolution, within an enterprise architecture context, of de jure and de facto standards by various actors in the milieu, industrial consortia, and international standardization committees active...

The Government of Québec is slowly but surely turning its attention to the issue of free and open source software in response to the interest shown by Québec's software industry and the attention paid to the phenomenon by governments around the world. This openness is easy to understand given...

The similarity between objects is a fundamental element of many learning algorithms. Most non-parametric methods take this similarity to be fixed, but much recent work has shown the advantages of learning it, in particular to exploit the local invariances in the data or to capture the possibly...

A standard model of the exploitation of a renewable resource by non-cooperating agents is considered. Under the assumption that the resource is sufficiently productive we prove that there exist infinitely many Markov-perfect Nash equilibria (MPNE). Although these equilibria lead to...

In this paper, we study and put under a common framework a number of non-linear dimensionality reduction methods, such as Locally Linear Embedding, Isomap, Laplacian Eigenmaps and kernel PCA, which are based on performing an eigen-decomposition (hence the name 'spectral'). That framework also...

The purpose of this study was to examine the role of country and technological intensity in the choice of compensation policies, and the influence of such policies on market performance and turnover in high and low technological intensity firms. Using a survey of 602 large firms in three...

Workflows (Wfs) are a major enabling technology for e-commerce. In our research, a Combined Negotiation (CN) is modeled and enacted using Wf technology. The modeling task captures the sequencing of the individual negotiations as well as the dependencies between them, and the enacting task runs...

Software agents (SA) could be useful in forming buyers' groups since humans have considerable difficulty in finding Pareto-optimal deals (no buyer can be better without another being worse) in negotiation situations. Then what are the computational and economical performances of SA for a...

We perform a theoretical investigation of the variance of the cross-validation estimate of the generalization error that takes into account the variability due to the choice of training sets and test examples. This allows us to propose two new estimators of this variance. We show, via...