Publication

The Virtue of Complexity in Return Prediction

Publications associées (27)

Impact of quantum-chemical metrics on the machine learning prediction of electron density

Anne-Clémence Corminboeuf, Ksenia Briling, Alberto Fabrizio

Machine learning (ML) algorithms have undergone an explosive development impacting every aspect of computational chemistry. To obtain reliable predictions, one needs to maintain a proper balance between the black-box nature of ML frameworks and the physics ...

AMER INST PHYSICS2021

Loss landscape and symmetries in Neural Networks

Mario Geiger

Neural networks (NNs) have been very successful in a variety of tasks ranging from machine translation to image classification. Despite their success, the reasons for their performance are still not well-understood. This thesis explores two main themes: lo ...

EPFL2021

Population pharmacokinetic model selection assisted by machine learning

Jan Sickmann Hesthaven, Nadia Terranova

A fit-for-purpose structural and statistical model is the first major requirement in population pharmacometric model development. In this manuscript we discuss how this complex and computationally intensive task could benefit from supervised machine learni ...

SPRINGER/PLENUM PUBLISHERS2022

Partitioning soil organic carbon into its centennially stable and active fractions with machine-learning models based on Rock-Eval (R) thermal analysis (PARTY(SOC)v2.0 and PARTY(SOC)v2.0 (EU))

Juan Carlos Quezada Rivera

Partitioning soil organic carbon (SOC) into two kinetically different fractions that are stable or active on a century scale is key for an improved monitoring of soil health and for more accurate models of the carbon cycle. However, all existing SOC fracti ...

COPERNICUS GESELLSCHAFT MBH2021

Machine learning based detection of digital documents maliciously recaptured from displays

Touradj Ebrahimi, Evgeniy Upenik, Saleh Gholam Zadeh

We used to say “seeing is believing": this is no longer true. The digitization is changing all aspects of life and business. One of the more noticeable impacts is in how business documents are being authored, exchanged and processed. Many documents such as ...

2020

Weight Erosion: An Update Aggregation Scheme for Personalized Collaborative Machine Learning

Martin Jaggi, Mary-Anne Hartley, Sai Praneeth Reddy Karimireddy, Felix Hans Michel Grimberg

Background. In medicine and other applications, the copying and sharing of data is impractical for a range of well-considered reasons. With federated learning (FL) techniques, machine learning models can be trained on data spread across several locations w ...

Springer, Cham2020

Multitask Learning Over Graphs: An Approach for Distributed, Streaming Machine Learning

Ali H. Sayed, Stefan Vlaski, Jie Chen, Roula Nassif

The problem of simultaneously learning several related tasks has received considerable attention in several domains, especially in machine learning, with the so-called multitask learning (MTL) problem, or learning to learn problem [1], [2]. MTL is an appro ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2020

Machine learning for metallurgy II. A neural-network potential for magnesium

William Curtin, Binglun Yin, Eleanor Yi Kei Mak

Interatomic potentials are essential for studying fundamental mechanisms of deformation and failure in metals and alloys because the relevant defects (dislocations, cracks, etc.) are far above the scales accessible to first-principles studies. Existing pot ...

2020

ResOT: Resource-Efficient Oblique Trees for Neural Signal Classification

Mahsa Shoaran, Bingzhao Zhu

Classifiers that can be implemented on chip with minimal computational and memory resources are essential for edge computing in emerging applications such as medical and IoT devices. This paper introduces a machine learning model based on oblique decision ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2020

Learning and leveraging shared domain semantics to counteract visual domain shifts

Róger Bermúdez Chacón

One of the main limitations of artificial intelligence today is its inability to adapt to unforeseen circumstances. Machine Learning (ML), due to its data-driven nature, is particularly susceptible to this. ML relies on observations in order to learn impli ...

EPFL2020