Mathieu Guillame-Bert
Software Engineer | Google Zurich
Google Zurich
Switzerland
e-mail:

Research Interests

My name is Mathieu Guillame-Bert, and I am working in Google Zurich, Switzerland.

I did my Postdoctoral at CMU (Carnegie Mellon University) in the Auton-Lab (part of Robotic Institute) under the supervision of Artur Dubrawski. I studied the use of rule extraction and decision forest-like techniques for symbolic and numerical time series. Typical applications include Automated and/or assisted Medical Diagnostics, Medical Forecasting, Human Activity Recognition and Forecasting, Banking Activity Patterns, Fault Detection and Prediction on complex systems, automatic Foreign exchange market trading, and a bit of Robotics.

I defended my PhD in France in 2012 at the INRIA Research Lab in the PRIMA team under the supervision of James L. Crowley. I studied the automated extraction of patterns from large temporal datasets, as well as the use of those models for automated prediction, user interpretation and automated reasoning.

I graduate from the Master of Advance Computing of the Imperial College of London, and from the "French Grande Ecole" ENSIMAG (Ecole Nationale Supérieure d'Informatique et de Mathématiques Appliquées) in 2009.

Publications

2022

Article

▪ Generative Trees: Adversarial and Copycat
Richard Nock and Mathieu Guillame-Bert
Arxiv
[paper ]

2020

Article

▪ Modeling Text with Decision Forests using Categorical-Set Splits
Mathieu Guillame-Bert, Sebastian Bruch, Petr Mitrichev, Petr Mikheev and Jan Pfeifer
Arxiv
[paper ] [source code ]

2018

Article

2017

Journals/Conference Proceedings

▪ Classification of Time Sequences using Graphs of Temporal Constraints
M. Guillame-Bert and A. Dubrawski.
Journal of Machine Learning Research 18 (2017)
[paper ] [source code ] [pig dataset ]

2016

Journals/Conference Proceedings

▪ Learning Temporal Rules to Forecast Instability in Continuously Monitored Patients
Mathieu Guillame-Bert, Artur Dubrawski, Donghan Wang, Marilyn Hravnak, Gilles Clermont, Michael R. Pinsky.
Journal of the American Medical Informatics Association (JAMIA), 2016

Tutorial

▪ Honey programming language tutorial
Mathieu Guillame-Bert
Introduction to the Honey programming language which is designed to efficiently process time structured datasets.
[html ]
▪ Event Viewer video tutorial
Mathieu Guillame-Bert
Introduction to the Event Viewer software which is designed to visualise large time structured datasets.
[html ]

Article

▪ Batched Lazy Decision Trees
Mathieu Guillame-Bert
ArXiv.org repository.
[arxiv ]

2015

Presentation

▪ Forecasting escalation of cardio-respiratory instability using noninvasive vital sign monitoring data
M. Guillame-Bert, A. Dubrawski, L. Chen, MT. Hravnak, G. Clermont, MR. Pinsky.
ESICM 2015 (European Society of Intensive Care Medicine)
▪ Detection of hemorrhage by analyzing shapes of the arterial blood pressure waveforms
S. Romero Zambrano, M. Guillame-Bert, A. Dubrawski, G. Clermont, MR. Pinsky
ESICM 2015 (European Society of Intensive Care Medicine)

2014

Workshop

▪ Learning Temporal Rules to Forecast Events in Multivariate Time Sequences
Mathieu Guillame-Bert and Artur Dubrawski
NIPS Workshop 2014 (Neural Information Processing Systems Foundation)

Presentation

▪ Utility of Empirical Models of Hemorrhage in Detecting and Quantifying Bleeding
Mathieu Guillame-Bert, Artur Dubrawski, Karen Chen, Andre Holder, Gilles Clermont, Marilyn Hravnak, and Michael Pinsky
ESICM 2014 (European Society of Intensive Care Medicine)

2013

Presentation

▪ Learning Temporal Rules to Forecast Instability in Intensive Care Patients
Mathieu Guillame-Bert, Artur Dubrawski, Karen Chen, Andre Holder, Gilles Clermont, Marilyn Hravnak and Michael Pinsky
ESICM 2013 (European Society of Intensive Care Medicine)
[read ]
▪ Learning Temporal Rules to Forecast Instability in Intensive Care Patients
Mathieu Guillame-Bert, Artur Dubrawski, Karen Chen, Andre Holder, Gilles Clermont, Marilyn Hravnak, and Michael Pinsky
INFORMS Healthcare 2013
▪ Artifact patterns in continuous noninvasive monitoring of patients
Hravnak M., Chen L., Bose E., Fiterau M., Guillame-Bert M., Dubrawski A., Clermont G., Pinsky MR.
INFORMS Healthcare 2013
▪ Is there an information hierarchy among hemodynamic variables for early identification of occult hemorrhage?
Andre Holder, Mathieu Guillame-Bert, Karen Chen, Peter Huggins, Artur Dubrawski, Marilyn Hravnak, Gilles Clermont, Michael Pinsky.
Journal of Critical Care vol 6
▪ Does advanced treatment of existing physiologic data allow for earlier detection of occult hemorrhage?
Holder A., Guillame-Bert M., Chen K., Huggins P., Dubrawski A., Hravnak M., Clermont G.
Journal of Critical Care vol 6

Tutorial

▪ The TITARL algorithm
Mathieu Guillame-Bert
An interactive tutorial to understand the TITARL algorithm (Data-Mining algorithm on symbolic time sequences).
[read ]

2012

Journals/Conference Proceedings

▪ Learning Temporal Association Rules on Symbolic Time Sequences
Mathieu Guillame-Bert and James L. Crowley
In Proceedings of the 2012 4th Asian Conference on Machine Learning, Singapore, 2012
[read ]
▪ Planning with Inaccurate Temporal Rules
Mathieu Guillame-Bert and James L. Crowley
In Proceedings of the 2012 IEEE 24rd International Conference on Tools with Artificial Intelligence, Athens, Greece, 2012
[read ]

Report

▪ PhD's Thesis, Learning Temporal Association Rules on Symbolic Time Sequences
Under the supervision of Pr. James L. CROWLEY
PRIMA Team - INRIA Lab. - Grenoble - France, 2012
Committee: Pr. Malik Gha llab, Pr. Paul Lukowicz, Dr. Artur Dubrawski, Pr. Augustin Lux
[read ]

Presentation

▪ Learning Temporal Association Rules on Symbolic Time Sequences
Mathieu Guillame-Bert
Extract of the thesis defense
[read ]

2011

Journals/Conference Proceedings

▪ New Approach on Temporal Data Mining for Symbolic Time Sequences: Temporal Tree Associate Rules
Mathieu Guillame-Bert and James L. Crowley
In Proceedings of the 2011 IEEE 23rd International Conference on Tools with Artificial Intelligence
[read ]
▪ Predicting Home Service Demands from Appliance Usage Data
Kaustav Basu, Mathieu Guillame-Bert, Hussein Joumaa, Stephane Ploix and James Crowley
In Proceedings of the 3rd International Conference on Information and Communication Technologies and Applications ICTA 2011
[read ]

2010

Journals/Conference Proceedings

▪ First-order Logic Learningin Artificial Neural Networks
Mathieu Guillame-Bert, Krysia Broda and Artur d'Avila Garcez
In Proceedings of 23rd International Joint Conference on Neural Networks IJCNN 2010
[read ]

Prior to 2010

Report

▪ Master's Thesis, Connectionist Artificial Neural Network
With the supervision of Krysia Broda
Imperial College of London, 2009
Distinguished MSc project [page]
[read ]
▪ Bs.C work, I-Terms unification
With the supervision of Nicolas Peltier
ENSIMAG, 2008
Download implementation (C++) [.zip]
[read ]
▲ Come back to index

Curriculum vitae

▲ Come back to index

Softwares & Datasets

Softwares

A collection of state-of-the-art algorithms for the training, serving and interpretation of Decision Forest models in TensorFlow's Keras.

Github page, TensorFlow.org page.

A C++ library containing a collection of state-of-the-art algorithms for the training, serving and interpretation of Decision Forest models.

Github page.

TITARL (2013)
TITARL (Temporal Interval Tree Association Rule Learner) is Temporal Data Mining algorithm able to extract temporal patterns and make prediction on symbolic time series and time sequences datasets. These patterns can then be used to user interpretation or for automatic forecasting.

Part of the MGB Framework.

Event Viewer is a powerful visualizing tool for time series, time sequences and other symbol or scalar temporal datasets. Event Viewer has unique features which allow for a powerful understanding of data. Event Viewer can be used to study static data and real time data flows. Event Viewer can interact seemingly with Honey

Part of the MGB Framework.

Honey (2016)
Honey is a compact and high level flow-oriented programming language designed to facilitate the pre/post processing and analysis of symbolic and numerical time series and sequences datasets. Honey can seemingly be applied on static dataset and real time data streams.

Part of the MGB Framework.

A small exploratory tool designed to test and experiment easily with several Machine Learning algorithms on several real work and sythetic datasets.

Download Machine Learning Lab.

Datasets

▲ Come back to index

Gallery

This sections shows some of the nice pictures that I have generated through my research work. You can click on the picture to get the full size versions.

You can see more of those pictures at the gallery page.

▲ Come back to index

Personal area

Social Projects

See the complete list of projects here.

Dust : The Abandoned Land is a multiplayer real-time survival roguelike that takes place in a large procedurally generated world populated with wildlife, dangerous creatures and other NPC humans (e.g. other survivors, military, bandits). The game includes some fun/interesting artificial intelligence (implemented though dynamic behavior trees).

The Raspberry Pi Camera Follower is a controller for a AIY Vision kit mounted on top of a Pan Tilt Hat and connected to a Raspberry Pi. The camera detects human faces and drive the pan/tilt to follow them [Video].

Mapgen Explorer is a terrain editor / debugger for the Cataclysm DDA game.

A screen-shot of Build & Defend
Build & Defend is a multi-player survival cooperative game in a randomly generated and destructible world. The game also include a lot of "social" logics: replay sharing, forum, chat, achievements, global leaderboard, custom character drawing, etc.. The game started as an experiment with game-play mechanics, and ended-up being a paying game. You can try this game at here.

Robot made of Legos
The core of a robot made of LEGOs
from when I was a kid.
This website contains many of previous projects, mostly video game development and DIYs.

The logo of Nac-sitter.com
I am the co-creator of the website http://nac-sitter.com/. Nac-sitter.com helps people to find somebody to keep their pets during holidays. This web-site focus mainly on NACs ("Nouveaux animaux de compagnie" - "New pets" in english) such as rats, hamsters, rabbits, fishs, pogonas, etc.


▲ Come back to index