background preloader

Apprentissage automatique : les réseaux de neurones

Apprentissage automatique : les réseaux de neurones

Related:  étude architecturesPsychologie cognitive

DIY Macrame Bracelet Growing up by the beach in Southern California, the ability to knot a macrame bracelet was practically a right of passage. Although those days are long behind us, we’ve never forgotten the ever-so-simple square knot technique. This time, however, we’re replacing hemp and wooden beads for more updated elements like colorful nylon cord and glossy metal charms. Happy knotting!

The Mathematician's Glossary of Non-Mathematical Terms All right. After having done some heavy-duty math this semester, we have decided to slack off a bit for good and ponder on, hmm…a different kind of mathematics altogether. “What?” 12 Steps to a Successful Proof of Concept - Part 3 by Andy Piper This series of articles is designed to give you a repeatable process for installing a proof of concept at a customer site in a manner that leads to a successful product evaluation and ultimately a sale. The first article focused on building a repeatable process for delivering a proof of concept. The second article explained how to understand what the customer needs, properly set their expectations and make sure everything is ready before you show up at the customer’s location. This article explains what to do during and after the customer visit to ensure a successful installation and keep the sales process moving forward. Step 9: Run through a checklist When you first arrive at the customer’s site, you need to get organized in order to make the most of the day.

UNIVERSITY OF GUELPH - 2009 - Résumé de thèse : Risk factor analysis of foodborne pathogen infection using statistic and soft computing approaches To develop appropriate prevention and control strategies for sporadic cases of illness, it is important to accurately model the system and analyze the risk factors. The objective of this study is to utilize both statistic and soft computing models to identify the significant risk factors for Salmonella Typhimurium DT104 and non-DT104 infection in Canada, and compare the findings. Previous studies have focused on analyzing each risk factor separately using single variable analysis, or modelling multiple risk factors using statistic models, such as logistic regression models. In this study, both neural network models and statistic models are developed and compared to determine which method produces superior results. Genetic algorithms are further incorporated to extract the optimal subset of factors that provide an accurate classification. In addition, neural network models are developed to study the effect of climatic factors for Salmonella infections.

Kano model The Kano model is a theory of product development and customer satisfaction developed in the 1980s by Professor Noriaki Kano, which classifies customer preferences into five categories. Categories[edit] These categories have been translated into English using various names (delighters/exciters, satisfiers, dissatisfiers, etc.), but all refer to the original articles written by Kano. Must-be Quality These attributes are taken for granted when fulfilled but result in dissatisfaction when not fulfilled.