A Multi-class Classification Strategy for Fisher Scores: Application to Signer Independent Sign Language Recognition

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Many applications, e.g. in content recommendation, sports, or recruitment, leverage the comparisons of alternatives to score those alternatives. The classical Bradley-Terry model and its variants have been widely used to do so. The historical model conside ...

Extracting maximal information from experimental data requires access to the likelihood function, which however is never directly available for complex experiments like those performed at high energy colliders. Theoretical predictions are obtained in this ...

In the rapidly evolving landscape of machine learning research, neural networks stand out with their ever-expanding number of parameters and reliance on increasingly large datasets. The financial cost and computational resources required for the training p ...

Modern integrated circuits are tiny yet incredibly complex technological artifacts, composed of millions and billions of individual structures working in unison. Managing their complexity and facilitating their design drove part of the co-evolution of mode ...

Dynamical system (DS) based motion planning offers collision-free motion, with closed-loop reactivity thanks to their analytical expression. It ensures that obstacles are not penetrated by reshaping a nominal DS through matrix modulation, which is construc ...

Machine learning (ML) enables artificial intelligent (AI) agents to learn autonomously from data obtained from their environment to perform tasks. Modern ML systems have proven to be extremely effective, reaching or even exceeding human intelligence. Altho ...

In light of the challenges posed by climate change and the goals of the Paris Agreement, electricity generation is shifting to a more renewable and decentralized pattern, while the operation of systems like buildings is increasingly electrified. This calls ...

In this paper, we propose an analytical stochastic dynamic programming (SDP) algorithm to address the optimal management problem of price-maker community energy storage. As a price-maker, energy storage smooths price differences, thus decreasing energy arb ...

In this thesis, we give new protocols that offer a quantum advantage for problems in ML, Physics, and Finance. Quantum mechanics gives predictions that are inconsistent with local realism. The experiment proving this fact (Bell, 1964) gives a quantum proto ...

Recent research shows prominent effects of pregnancy and the parenthood transition on structural brain characteristics in humans. Here, we present a comprehensive study of how parental status and number of children born/fathered links to markers of brain a ...

The remarkable ability of deep learning (DL) models to approximate high-dimensional functions from samples has sparked a revolution across numerous scientific and industrial domains that cannot be overemphasized. In sensitive applications, the good perform ...

Current transformer-based skeletal action recognition models tend to focus on a limited set of joints and low-level motion patterns to predict action classes. This results in significant performance degradation under small skeleton perturbations or changin ...

Decision-making permeates every aspect of human and societal development, from individuals' daily choices to the complex decisions made by communities and institutions. Central to effective decision-making is the discipline of optimization, which seeks th ...

Informative sample selection in an active learning (AL) setting helps a machine learning system attain optimum performance with minimum labeled samples, thus reducing annotation costs and boosting performance of computer-aided diagnosis systems in the pres ...

Given a sequence of functions

f_1,\ldots,f_n

with

f_i:\mathcal{D}\mapsto \mathbb{R}

, finite-sum minimization seeks a point

{x}^\star \in \mathcal{D}

minimizing

\sum_{j=1}^nf_j(x)/n

. In this work, we propose a key twist into the finite-sum minimizat ...

Laser Powder Bed Fusion (LPBF) is an Additive Manufacturing (AM) process consolidating parts layer by layer, from a metallic powder bed. It allows no limitation in terms of geometry and is therefore of particular interest to various industries. Metallic LP ...

Learning-based outlier (mismatched correspondence) rejection for robust 3D registration generally formulates the outlier removal as an inlier/outlier classification problem. The core for this to be successful is to learn the discriminative inlier/outlier f ...

We consider the problem of learning a target function corresponding to a deep, extensive-width, non-linear neural network with random Gaussian weights. We consider the asymptotic limit where the number of samples, the input dimension and the network width ...

Epilepsy is a common chronic neurological disorder that causes recurring seizures and affects more than 50 million people worldwide. Implantable medical devices (IMDs) are regarded as effective tools to cure patients who suffer from refractory epilepsy. Se ...

The Euclid Space Telescope will provide deep imaging at optical and near-infrared wavelengths, along with slitless near-infrared spectroscopy, across similar to 15 000deg(2) of the sky. Euclid is expected to detect similar to 12 billion astronomical source ...

A Multi-class Classification Strategy for Fisher Scores: Application to Signer Independent Sign Language Recognition

Chat with Graph Search

Generalized Bradley-Terry Models for Score Estimation from Paired Comparisons

Boosting likelihood learning with event reweighting

Random matrix methods for high-dimensional machine learning models

Graph generative deep learning models with an application to circuit topologies

Reactive collision-free motion generation in joint space via dynamical systems and sampling-based MPC

Few-shot Learning for Efficient and Effective Machine Learning Model Adaptation

Quantifying the Unknown: Data-Driven Approaches and Applications in Energy Systems

Energy Management of Price-Maker Community Energy Storage by Stochastic Dynamic Programming

Quantum Protocols for ML, Physics, and Finance

Parental status and markers of brain and cellular age: A 3D convolutional network and classification study

Towards Trustworthy Deep Learning for Image Reconstruction

MaskCLR: Attention-Guided Contrastive Learning for Robust Action Representation Learning

Reliable data-driven decision-making through optimal transport

GANDALF: Graph-based transformer and Data Augmentation Active Learning Framework with interpretable features for multi-label chest Xray classification

Efficient Continual Finite-Sum Minimization

Towards Robust Monitoring of the Laser Powder Bed Fusion Process based on Acoustic Emission combined with Machine Learning Solutions

Robust Outlier Rejection for 3D Registration with Variational Bayes

Bayes-optimal Learning of Deep Random Networks of Extensive-width

Hardware Implementation of Digital Signal Processing Algorithms for Programmable Epilepsy Control Systems

Euclid preparation XXII. Selection of quiescent galaxies from mock photometry using machine learning