Publications associées à Learning from the past: A short term forecast method for the COVID-19 incidence curve

Publications associées (14)

Parsimonious Online Learning with Kernels and Random Features with Applications to Stochastic Optimal Control

This thesis explores stochastic optimal control through three interconnected contributions: a theoretical framework, and the development of two regression methods, POLK and POLRF, tailored to high-dimensional regression challenges in this domain. In the f ...

EPFL2025

ChromatinHD connects single-cell DNA accessibility and conformation to gene expression through scale-adaptive machine learning

Bart Deplancke, Wouter Jozef L Saelens, Olga Pushkarev

Gene regulation is inherently multiscale, but scale-adaptive machine learning methods that fully exploit this property in single-nucleus accessibility data are still lacking. Here, we develop ChromatinHD, a pair of scale-adaptive models that uses the raw a ...

Nature Research2025

Robust Classification Using Contractive Hamiltonian Neural ODEs

Giancarlo Ferrari Trecate, Muhammad Zakwan, Liang Xu

Deep neural networks can be fragile and sensitive to small input perturbations that might cause a significant change in the output. In this letter, we employ contraction theory to improve the robustness of neural ODEs (NODEs). A dynamical system is contrac ...

2022

NeuralTree: A 256-Channel 0.227-mu J/Class Versatile Neural Activity Classification and Closed-Loop Neuromodulation SoC

Stéphanie Lacour, Mahsa Shoaran, Bingzhao Zhu, Uisub Shin, Alix Esther Anne Trouillet, Cong Ding, Emilie Cornelia Maria Revol, Yashwanth Sai Reddy Vyza

Closed-loop neural interfaces with on-chip machine learning can detect and suppress disease symptoms in neurological disorders or restore lost functions in paralyzed patients. While high-density neural recording can provide rich neural activity information ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2022

Fidelity Estimation Improves Noisy-Image Classification with Pretrained Networks

Sabine Süsstrunk, Majed El Helou, Deblina Bhattacharjee

Image classification has significantly improved using deep learning. This is mainly due to convolutional neural networks (CNNs) that are capable of learning rich feature extractors from large datasets. However, most deep learning classification methods are ...

IEEE Institute of Electrical and Electronics Engineers2021

Scalable and Efficient Comparison-based Search without Features

Matthias Grossglauser, Lucas Maystre, Daniyar Chumbalov

We consider the problem of finding a target object t using pairwise comparisons, by asking an oracle questions of the form “Which object from the pair (i, j) is more similar to t?”. Objects live in a space of latent features, from which the oracle generate ...

JMLR-JOURNAL MACHINE LEARNING RESEARCH2020

Time course of prediction errors in sequential decision making

Michael Herzog, He Xu

In reinforcement learning, an agent makes sequential decisions to maximize reward. During learning, the actual and expected outcome are compared to tell whether a decision was good or bad. The difference between the actual outcome and expected outcome is t ...

2018

Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks

Alexandre Massoud Alahi

Understanding human motion behavior is critical for autonomous moving platforms (like self-driving cars and social robots) if they are to navigate human-centric environments. This is challenging because human motion is inherently multimodal: given a histor ...

2018

Automatic Hand Phantom Map Detection Methods

Christian Enz, Claudio Bruschini, Jörn Justiz, Huaiqi Huang

Many amputees have maps of referred sensation from their missing hand on their residual limb (phantom maps). This skin area can serve as a target for providing amputees with tactile sensory feedback. Providing tactile feedback on the phantom map can improv ...

2015

Spectral modeling of time series with missing data

Singular spectrum analysis is a natural generalization of principal component methods for time series data. In this paper we propose an imputation method to be used with singular spectrum-based techniques which is based on a weighted combination of the for ...

Elsevier2013

Refining Regulatory Networks through Phylogenetic Transfer of Information

Bernard Moret, Xiuwei Zhang

The experimental determination of transcriptional regulatory networks in the laboratory remains difficult and time-consuming, while computational methods to infer these networks provide only modest accuracy. The latter can be attributed partly to the limit ...

2012

Code-specific policy gradient rules for spiking neurons

Wulfram Gerstner, Guillaume Hennequin

Although it is widely believed that reinforcement learning is a suitable tool for describing behavioral learning, the mechanisms by which it can be implemented in networks of spiking neurons are not fully understood. Here, we show that different learning r ...

Massachusetts Institute of Technology Press2009

Distributed Scalable Multi-Robot Learning using Particle Swarm Optimization

Alcherio Martinoli

Designing effective behavioral controllers for mobile robots can be difficult and tedious; this process can be circumvented by using online learning techniques which allow robots to generate their own controllers online in an automated fash- ion. In multi- ...

2009

Principled Detection-by-Classification from Multiple Views

Pascal Fua, François Fleuret

Machine-learning based classification techniques have been shown to be effective at detecting objects in complex scenes. However, the final results are often obtained from the alarms produced by the classifiers through a post-processing which typically rel ...

2008