Data Science
Network profile
691
reputation
13

Matthieu Brucher

I'm a C++ and Python developer interested in High Performance Computing as well as Machine Learning.

I worked on several large scale projects for supercomputers and also on Machine Learning algorithms for day to day professional usage.

One of the authors of "Building Machine Learning Systems with Python" (3rd edition).

Former scikit-learn participant.

Maintainer of Audio ToolKit (https://github.com/mbrucher/AudioTK/)

32
answers
0
questions
~6k
people reached
  • Londres, Royaume-Uni
  • audio-tk.com
  • Member for 10 months
  • 32 profile views
  • Last seen Jul 7 at 10:07

Communities (24)

Top network posts

Top tags (48)

Score 12
Posts 11
Posts % 34
Score 11
Posts 11
Score 7
Posts 8
Score 5
Posts 3
Score 4
Posts 4
Score 4
Posts 2
View all tags →

Top posts (32) All Questions Answers | Votes Newest

4 Is Overfitting always bad? Jan 4
4 AUC ROC in keras is different when using tensorflow or scikit functions. Dec 28 '18
3 Intuition behind using the inverse of a Hessian matrix for automatically estimating the learning rate (aggression parameter) in gradient descent. Dec 26 '18
3 PCA: projection of positive data on negative side of plane Dec 23 '18
2 LSTM vs ARIMA for demand prediction Dec 30 '18
2 Methods of building machine learning models Dec 19 '18
2 Adding variables to Random Forest decreases performance Dec 19 '18
2 What's a difference between the neoperceptron and CNN? Oct 26 '18
1 Product of dot products in neural network Feb 13
1 Normalization before or after resizing Jan 21
View all questions and answers →

Badges (13)

Gold

—

Silver

—

Bronze

13

Rarest

View all badges →