Publications associées à Diagramme d'influence

Automatic Parameterization for Aerodynamic Shape Optimization via Deep Geometric Learning

We propose two deep learning models that fully automate shape parameterization for aerodynamic shape optimization. Both models are optimized to parameterize via deep geometric learning to embed human prior knowledge into learned geometric patterns, elimina ...

2023

Automatic Uniform Quantum State Preparation Using Decision Diagrams

Giovanni De Micheli, Mathias Soeken, Fereshte Mozafari Ghoraba, Heinz Riener

Most quantum algorithms assume some specific initial state in superposition of basis states before performing the desired application-specific computations. The preparation of such states itself requires a computation performed by a quantum circuit. In thi ...

IEEE COMPUTER SOC2020

Information Theoretic Characterization of Uncertainty Distinguishes Surprise From Accuracy Signals in the Brain

Leyla Loued-Khenissi, Kerstin Preuschoff

Uncertainty presents a problem for both human and machine decision-making. While utility maximization has traditionally been viewed as the motive force behind choice behavior, it has been theorized that uncertainty minimization may supersede reward motivat ...

2020

Quantification of the conditional value of SHM data for the fatigue safety evaluation of a road viaduct

Eugen Brühwiler, Imane Bayane

Fatigue safety verification of existing bridges that uses ‘‘re-calculation’’ based on codes, usually results in insufficient fatigue safety, triggering invasive interventions. Instead of “re-calculation”, Structural Health Monitoring (SHM) should be used f ...

2019

One-shot learning and behavioral eligibility traces in sequential decision making

Michael Herzog, Wulfram Gerstner, Marco Philipp Lehmann, Kerstin Preuschoff, He Xu, Vasiliki Liakoni

In many daily tasks, we make multiple decisions before reaching a goal. In order to learn such sequences of decisions, a mechanism to link earlier actions to later reward is necessary. Reinforcement learning (RL) theory suggests two classes of algorithms s ...

2019

Optimal Information Collection Policies in a Markov Decision Process Framework

Thomas Alois Weber

The cost-effectiveness and value of additional information about a health technology or program may change over time because of trends affecting patient cohorts and/or the intervention. Delaying information collection even for parameters that do not change ...

2018

One-shot learning and eligibility traces in sequential decision making

Marco Philipp Lehmann

When humans or animals perform an action that led to a desired outcome, they show a tendency to repeat it. The mechanisms underlying learning from past experience and adapting future behavior are still not fully understood. In this thesis, I study how huma ...

EPFL2018

What to Choose Next? A Paradigm for Testing Human Sequential Decision Making

Michael Herzog, Aaron Michael Clarke, Elisa Tartaglia

Many of the decisions we make in our everyday lives are sequential and entail sparse rewards. While sequential decision-making has been extensively investigated in theory (e.g., by reinforcement learning models) there is no systematic experimental paradigm ...

Frontiers Media2017

Neural Correlates of Sequential Decision Making

Michael Herzog, He Xu

In chess, a series of moves is made until a delayed sparse feedback (win, loss) is issued, which makes it impossible to evaluate the value of a single move. There are powerful reinforcement learning (RL) algorithms, which can cope with these sequential dec ...

2017

Neural Correlates of Sequential Decision Making

Michael Herzog, He Xu

In chess, a series of moves is made until a delayed sparse feedback (win, loss) is issued, which makes it impossible to evaluate the value of a single move. There are powerful reinforcement learning (RL) algorithms, which can cope with these sequential dec ...

2017