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

Seeking the new, learning from the unexpected: Computational models of surprise and novelty in the brain

Human babies have a natural desire to interact with new toys and objects, through which they learn how the world around them works, e.g., that glass shatters when dropped, but a rubber ball does not. When their predictions are proven incorrect, such as whe ...

EPFL2024

Unveiling the complexity of learning and decision-making

Wei-Hsiang Lin

Reinforcement learning (RL) is crucial for learning to adapt to new environments. In RL, the prediction error is an important component that compares the expected and actual rewards. Dopamine plays a critical role in encoding these prediction errors. In my ...

EPFL2024

Predicting the long-term collective behaviour of fish pairs with deep learning

Francesco Mondada, Alexandre Massoud Alahi, Vaios Papaspyros

Modern computing has enhanced our understanding of how social interactions shape collective behaviour in animal societies. Although analytical models dominate in studying collective behaviour, this study introduces a deep learning model to assess social in ...

2024

Incorporating Projective Geometry into Deep Learning

Michal Jan Tyszkiewicz

In this thesis we explore the applications of projective geometry, a mathematical theory of the relation between 3D scenes and their 2D images, in modern learning-based computer vision systems. This is an interesting research question which contradicts the ...

EPFL2024

Inverse design of metal-organic frameworks for direct air capture of CO2via deep reinforcement learning

Berend Smit, Sauradeep Majumdar, Xiaoqi Zhang, Hyunsoo Park

The combination of several interesting characteristics makes metal-organic frameworks (MOFs) a highly sought-after class of nanomaterials for a broad range of applications like gas storage and separation, catalysis, drug delivery, and so on. However, the e ...

Royal Soc Chemistry2024

Fusing Pre-existing Knowledge and Machine Learning for Enhanced Building Thermal Modeling and Control

Loris Di Natale

Buildings play a pivotal role in the ongoing worldwide energy transition, accounting for 30% of the global energy consumption. With traditional engineering solutions reaching their limits to tackle such large-scale problems, data-driven methods and Machine ...

EPFL2024

Multi-temporal forest monitoring in the Swiss Alps with knowledge-guided deep learning

Devis Tuia, Thiên-Anh Claris Nguyen, Marc Conrad Russwurm, Gaston Jean Lenczner

Monitoring forests, in particular their response to climate and land use change, requires studying long time scales. While efficient deep learning methods have been developed to process short time series of satellite imagery, leveraging long time series of ...

Elsevier Science Inc2024

Towards practical reinforcement learning for tokamak magnetic control

Jonas Buchli, Federico Alberto Alfredo Felici, Cristian Galperti, Brendan Tracey

Reinforcement learning (RL) has shown promising results for real-time control systems, including the domain of plasma magnetic control. However, there are still significant drawbacks compared to traditional feedback control approaches for magnetic confinem ...

Elsevier Science Sa2024

Understanding generalization and robustness in modern deep learning

Maksym Andriushchenko

In this thesis, we study two closely related directions: robustness and generalization in modern deep learning. Deep learning models based on empirical risk minimization are known to be often non-robust to small, worst-case perturbations known as adversari ...

EPFL2024

Reliable data-driven decision-making through optimal transport

Bahar Taskesen

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 ...

EPFL2024

Performing and Detecting Backdoor Attacks on Face Recognition Algorithms

Alexander Carl Unnervik

The field of biometrics, and especially face recognition, has seen a wide-spread adoption the last few years, from access control on personal devices such as phones and laptops, to automated border controls such as in airports. The stakes are increasingly ...

EPFL2024

Non-invasive stimulation of the human striatum disrupts reinforcement learning of motor skills

Elena Beanato, Esra Neufeld, Friedhelm Christoph Hummel, Takuya Morishita, Maximilian Jonas Wessel, Traian Popa, Pierre Theopistos Vassiliadis, Julie Duqué, Fabienne Windel

Reinforcement feedback can improve motor learning, but the underlying brain mechanisms remain underexplored. In particular, the causal contribution of specific patterns of oscillatory activity within the human striatum is unknown. To address this question, ...

Nature Portfolio2024

Generalization and Personalization of Machine Learning for Multimodal Mobile Sensing in Everyday Life

Lakmal Buddika Meegahapola

A range of behavioral and contextual factors, including eating and drinking behavior, mood, social context, and other daily activities, can significantly impact an individual's quality of life and overall well-being. Therefore, inferring everyday life aspe ...

EPFL2024

Augmented Memory: Sample-Efficient Generative Molecular Design with Reinforcement Learning

Philippe Schwaller, Jeff Guo

Sample efficiency is a fundamental challenge in de novo molecular design. Ideally, molecular generative models should learn to satisfy a desired objective under minimal calls to oracles (computational property predictors). This problem becomes more apparen ...

Amer Chemical Soc2024

Glenohumeral joint force prediction with deep learning

Dominique Pioletti, Alexandre Terrier, Philippe Büchler, Patrick Goetti

Deep learning models (DLM) are efficient replacements for computationally intensive optimization techniques. Musculoskeletal models (MSM) typically involve resource-intensive optimization processes for determining joint and muscle forces. Consequently, DLM ...

Elsevier Sci Ltd2024

Resource-Efficient Continual Learning for Personalized Online Seizure Detection

David Atienza Alonso, Giovanni Ansaloni, Flavio Ponzina, Amirhossein Shahbazinia, José Angel Miranda Calero, Jonathan Dan

Epilepsy, a major neurological disease, requires careful diagnosis and treatment. However, the detection of epileptic seizures remains a significant challenge. Current clinical practice relies on expert analysis of EEG signals, a process that is time-consu ...

IEEE2024

Deep learning approach for identification of H II regions during reionization in 21-cm observations - II. Foreground contamination

Michele Bianco, Jean-Paul Richard Kneib, Emma Elizabeth Tolley, Tianyue Chen

The upcoming Square Kilometre Array Observatory will produce images of neutral hydrogen distribution during the epoch of reionization by observing the corresponding 21-cm signal. However, the 21-cm signal will be subject to instrumental limitations such as ...

Oxford Univ Press2024

End-to-End Learning for Stochastic Optimization: A Bayesian Perspective

Daniel Kuhn, Yves Rychener, Tobias Sutter

We develop a principled approach to end-to-end learning in stochastic optimization. First, we show that the standard end-to-end learning algorithm admits a Bayesian interpretation and trains a posterior Bayes action map. Building on the insights of this an ...

2023

Reinforcement learning approach to control an inverted pendulum: A general framework for educational purposes

Jesus Sanchez Rodriguez

Machine learning is often cited as a new paradigm in control theory, but is also often viewed as empirical and less intuitive for students than classical model-based methods. This is particularly the case for reinforcement learning, an approach that does n ...

PUBLIC LIBRARY SCIENCE2023

Computationally Efficient Reinforcement Learning: Targeted Exploration leveraging Simple Rules

Colin Neil Jones, Loris Di Natale, Bratislav Svetozarevic

Model-free Reinforcement Learning (RL) generally suffers from poor sample complexity, mostly due to the need to exhaustively explore the state-action space to find well-performing policies. On the other hand, we postulate that expert knowledge of the syste ...

2023