7 Questions 88 Answers 0 Followers
Questions related from Raphaël Feraud
For a lot of applications, such as recommendation, adserving, personnalization, marketing optimization, user's information (navigation logs, service logs, calls, purchases...) is stored and...
04 April 2016 5,261 16 View
For instance: - datasets for supervised classification, with a lot instances to simulate a data stream and many classes to simulate the playable actions, - or datasets with contexts, actions and...
09 September 2014 9,183 1 View
Galileo has deduced the law of gravity (1/2 g t^2) by observing balls rolling on an inclined plane. However, without the occam razor, there is no reason to infirm the following law: until today...
10 October 2013 8,652 37 View
Deep learners report very good results on a lot of difficult learning tasks such as Speech recognition, Object Recognition, Natural Language processing, Transfer learning... The hidden layers are...
07 July 2013 8,119 6 View
"The nature of statistical learning theory" was my favorite book during my PhD, and several years after. I still use "Elements of Information Theory" in my work. Recently a book has opened new...
04 April 2013 5,331 32 View
We consider a data stream which is not necessary stationary. We would like to label instance on the fly.
04 April 2013 6,702 4 View
One of the claims of "Big Data" is to increase the performances of the predictors. Then, to achieve this goal, the right way is: Online learning on the data stream? Bagging techniques on a Hadoop...
04 April 2013 1,533 2 View