Search Results for author: Frederic Precioso

Found 17 papers, 8 papers with code

Attention Meets Post-hoc Interpretability: A Mathematical Perspective

1 code implementation5 Feb 2024 Gianluigi Lopardo, Frederic Precioso, Damien Garreau

Attention-based architectures, in particular transformers, are at the heart of a technological revolution.

Visual Objectification in Films: Towards a New AI Task for Video Interpretation

no code implementations24 Jan 2024 Julie Tores, Lucile Sassatelli, Hui-Yin Wu, Clement Bergman, Lea Andolfi, Victor Ecrement, Frederic Precioso, Thierry Devars, Magali Guaresi, Virginie Julliard, Sarah Lecossais

In film gender studies, the concept of 'male gaze' refers to the way the characters are portrayed on-screen as objects of desire rather than subjects.

Faithful and Robust Local Interpretability for Textual Predictions

1 code implementation30 Oct 2023 Gianluigi Lopardo, Frederic Precioso, Damien Garreau

Interpretability is essential for machine learning models to be trusted and deployed in critical domains.

Understanding Post-hoc Explainers: The Case of Anchors

no code implementations15 Mar 2023 Gianluigi Lopardo, Frederic Precioso, Damien Garreau

In many scenarios, the interpretability of machine learning models is a highly required but difficult task.

Generalised Mutual Information for Discriminative Clustering

1 code implementation12 Oct 2022 Louis Ohl, Pierre-Alexandre Mattei, Charles Bouveyron, Warith Harchaoui, Mickaël Leclercq, Arnaud Droit, Frederic Precioso

In the last decade, recent successes in deep clustering majorly involved the mutual information (MI) as an unsupervised objective for training neural networks with increasing regularisations.

Clustering Deep Clustering

A Sea of Words: An In-Depth Analysis of Anchors for Text Data

1 code implementation27 May 2022 Gianluigi Lopardo, Frederic Precioso, Damien Garreau

For text data, it proposes to explain a decision by highlighting a small set of words (an anchor) such that the model to explain has similar outputs when they are present in a document.

text-classification Text Classification

SMACE: A New Method for the Interpretability of Composite Decision Systems

1 code implementation16 Nov 2021 Gianluigi Lopardo, Damien Garreau, Frederic Precioso, Greger Ottosson

To explain such decisions, we propose the Semi-Model-Agnostic Contextual Explainer (SMACE), a new interpretability method that combines a geometric approach for decision rules with existing interpretability methods for machine learning models to generate an intuitive feature ranking tailored to the end user.

BIG-bench Machine Learning

Revisiting Deep Architectures for Head Motion Prediction in 360° Videos

no code implementations26 Nov 2019 Miguel Fabian Romero Rondon, Lucile Sassatelli, Ramon Aparicio Pardo, Frederic Precioso

A root-cause analysis of the metrics, datasets and neural architectures shows in particular that (i) the content can inform the prediction for horizons longer than 2 to 3 sec.

motion prediction Time Series Analysis

Adaptive Bayesian Linear Regression for Automated Machine Learning

no code implementations1 Apr 2019 Weilin Zhou, Frederic Precioso

To solve a machine learning problem, one typically needs to perform data preprocessing, modeling, and hyperparameter tuning, which is known as model selection and hyperparameter optimization. The goal of automated machine learning (AutoML) is to design methods that can automatically perform model selection and hyperparameter optimization without human interventions for a given dataset.

Bayesian Optimization BIG-bench Machine Learning +4

Textual Deconvolution Saliency (TDS) : a deep tool box for linguistic analysis

no code implementations ACL 2018 Laurent Vanni, Melanie Ducoffe, Carlos Aguilar, Frederic Precioso, Damon Mayaffre

In this paper, we propose a new strategy, called Text Deconvolution Saliency (TDS), to visualize linguistic information detected by a CNN for text classification.

General Classification text-classification +1

QBDC: Query by dropout committee for training deep supervised architecture

no code implementations19 Nov 2015 Melanie Ducoffe, Frederic Precioso

While the current trend is to increase the depth of neural networks to increase their performance, the size of their training database has to grow accordingly.

Active Learning

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