Search Results for author: François Laviolette

Found 28 papers, 12 papers with code

Multinational Address Parsing: A Zero-Shot Evaluation

1 code implementation7 Dec 2021 Marouane Yassine, David Beauchemin, François Laviolette, Luc Lamontagne

While these models yield notable results, previous work on neural networks has only focused on parsing addresses from a single source country.

Transfer Learning

PAC-Bayesian Learning of Aggregated Binary Activated Neural Networks with Probabilities over Representations

no code implementations28 Oct 2021 Louis Fortier-Dubois, Gaël Letarte, Benjamin Leblanc, François Laviolette, Pascal Germain

Considering a probability distribution over parameters is known as an efficient strategy to learn a neural network with non-differentiable activation functions.

Generalization Bounds

Out-of-distribution detection for regression tasks: parameter versus predictor entropy

no code implementations24 Oct 2020 Yann Pequignot, Mathieu Alain, Patrick Dallaire, Alireza Yeganehparast, Pascal Germain, Josée Desharnais, François Laviolette

Focusing on regression tasks, we choose a simple yet insightful model for this OOD distribution and conduct an empirical evaluation of the ability of various methods to discriminate OOD samples from the data.

Out-of-Distribution Detection Out of Distribution (OOD) Detection +2

Leveraging Subword Embeddings for Multinational Address Parsing

3 code implementations29 Jun 2020 Marouane Yassine, David Beauchemin, François Laviolette, Luc Lamontagne

We propose an approach in which we employ subword embeddings and a Recurrent Neural Network architecture to build a single model capable of learning to parse addresses from multiple countries at the same time while taking into account the difference in languages and address formatting systems.

Transfer Learning

A Transferable Adaptive Domain Adversarial Neural Network for Virtual Reality Augmented EMG-Based Gesture Recognition

1 code implementation16 Dec 2019 Ulysse Côté-Allard, Gabriel Gagnon-Turcotte, Angkoon Phinyomark, Kyrre Glette, Erik Scheme, François Laviolette, Benoit Gosselin

The ability of the dynamic dataset to serve as a benchmark is leveraged to evaluate the impact of different recalibration techniques for long-term (across-day) gesture recognition, including a novel algorithm, named TADANN.

EMG Gesture Recognition Gesture Recognition +1

Interpreting Deep Learning Features for Myoelectric Control: A Comparison with Handcrafted Features

1 code implementation30 Nov 2019 Ulysse Côté-Allard, Evan Campbell, Angkoon Phinyomark, François Laviolette, Benoit Gosselin, Erik Scheme

Using ADANN-generated features, the main contribution of this work is to provide the first topological data analysis of EMG-based gesture recognition for the characterisation of the information encoded within a deep network, using handcrafted features as landmarks.

Feature Engineering Gesture Recognition +1

MODELLING BIOLOGICAL ASSAYS WITH ADAPTIVE DEEP KERNEL LEARNING

no code implementations25 Sep 2019 Prudencio Tossou, Basile Dura, Daniel Cohen, Mario Marchand, François Laviolette, Alexandre Lacoste

Due to the significant costs of data generation, many prediction tasks within drug discovery are by nature few-shot regression (FSR) problems, including accurate modelling of biological assays.

Drug Discovery

Deep Learning for Electromyographic Hand Gesture Signal Classification Using Transfer Learning

4 code implementations10 Jan 2018 Ulysse Côté-Allard, Cheikh Latyr Fall, Alexandre Drouin, Alexandre Campeau-Lecours, Clément Gosselin, Kyrre Glette, François Laviolette, Benoit Gosselin

Consequently, this paper proposes applying transfer learning on aggregated data from multiple users, while leveraging the capacity of deep learning algorithms to learn discriminant features from large datasets.

EMG Gesture Recognition General Classification +2

Maximum Margin Interval Trees

1 code implementation NeurIPS 2017 Alexandre Drouin, Toby Dylan Hocking, François Laviolette

Learning a regression function using censored or interval-valued output data is an important problem in fields such as genomics and medicine.

regression

PAC-Bayes and Domain Adaptation

no code implementations17 Jul 2017 Pascal Germain, Amaury Habrard, François Laviolette, Emilie Morvant

Firstly, we propose an improvement of the previous approach we proposed in Germain et al. (2013), which relies on a novel distribution pseudodistance based on a disagreement averaging, allowing us to derive a new tighter domain adaptation bound for the target risk.

Domain Adaptation Generalization Bounds

Large scale modeling of antimicrobial resistance with interpretable classifiers

1 code implementation3 Dec 2016 Alexandre Drouin, Frédéric Raymond, Gaël Letarte St-Pierre, Mario Marchand, Jacques Corbeil, François Laviolette

Antimicrobial resistance is an important public health concern that has implications in the practice of medicine worldwide.

A New PAC-Bayesian Perspective on Domain Adaptation

1 code implementation15 Jun 2015 Pascal Germain, Amaury Habrard, François Laviolette, Emilie Morvant

We study the issue of PAC-Bayesian domain adaptation: We want to learn, from a source domain, a majority vote model dedicated to a target one.

Domain Adaptation

Efficient Learning of Ensembles with QuadBoost

no code implementations8 Jun 2015 Louis Fortier-Dubois, François Laviolette, Mario Marchand, Louis-Emile Robitaille, Jean-Francis Roy

We first present a general risk bound for ensembles that depends on the Lp norm of the weighted combination of voters which can be selected from a continuous set.

Domain-Adversarial Training of Neural Networks

35 code implementations28 May 2015 Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, François Laviolette, Mario Marchand, Victor Lempitsky

Our approach is directly inspired by the theory on domain adaptation suggesting that, for effective domain transfer to be achieved, predictions must be made based on features that cannot discriminate between the training (source) and test (target) domains.

Domain Generalization General Classification +5

PAC-Bayesian Theorems for Domain Adaptation with Specialization to Linear Classifiers

no code implementations24 Mar 2015 Pascal Germain, Amaury Habrard, François Laviolette, Emilie Morvant

In this paper, we provide two main contributions in PAC-Bayesian theory for domain adaptation where the objective is to learn, from a source distribution, a well-performing majority vote on a different target distribution.

Domain Adaptation

Domain-Adversarial Neural Networks

1 code implementation15 Dec 2014 Hana Ajakan, Pascal Germain, Hugo Larochelle, François Laviolette, Mario Marchand

We propose a training objective that implements this idea in the context of a neural network, whose hidden layer is trained to be predictive of the classification task, but uninformative as to the domain of the input.

Denoising Domain Adaptation +3

On the String Kernel Pre-Image Problem with Applications in Drug Discovery

no code implementations3 Dec 2014 Sébastien Giguère, Amélie Rolland, François Laviolette, Mario Marchand

This work uses a recent result on combinatorial optimization of linear predictors based on string kernels to develop, for the pre-image, a low complexity upper bound valid for many string kernels.

Combinatorial Optimization Drug Discovery +1

On the Generalization of the C-Bound to Structured Output Ensemble Methods

no code implementations6 Aug 2014 François Laviolette, Emilie Morvant, Liva Ralaivola, Jean-Francis Roy

This paper generalizes an important result from the PAC-Bayesian literature for binary classification to the case of ensemble methods for structured outputs.

Binary Classification General Classification

Sequential Model-Based Ensemble Optimization

no code implementations4 Feb 2014 Alexandre Lacoste, Hugo Larochelle, François Laviolette, Mario Marchand

One of the most tedious tasks in the application of machine learning is model selection, i. e. hyperparameter selection.

Model Selection

PAC-Bayesian Analysis of Contextual Bandits

no code implementations NeurIPS 2011 Yevgeny Seldin, Peter Auer, John S. Shawe-Taylor, Ronald Ortner, François Laviolette

The scaling of our regret bound with the number of states (contexts) $N$ goes as $\sqrt{N I_{\rho_t}(S;A)}$, where $I_{\rho_t}(S;A)$ is the mutual information between states and actions (the side information) used by the algorithm at round $t$.

Multi-Armed Bandits

From PAC-Bayes Bounds to KL Regularization

no code implementations NeurIPS 2009 Pascal Germain, Alexandre Lacasse, Mario Marchand, Sara Shanian, François Laviolette

We show that standard ell_p-regularized objective functions currently used, such as ridge regression and ell_p-regularized boosting, are obtained from a relaxation of the KL divergence between the quasi uniform posterior and the uniform prior.

regression

A Transductive Bound for the Voted Classifier with an Application to Semi-supervised Learning

no code implementations NeurIPS 2008 Massih Amini, Nicolas Usunier, François Laviolette

In this case, we propose a second bound on the joint probability that the voted classifier makes an error over an example having its margin over a fixed threshold.

Self-Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.