Esprit critique

Publications associées (29)

À propos
Confidentialité
Mentions légales

Graph Chatbot

The inductive bias of deep learning: Connecting weights and functions

Guillermo Ortiz Jimenez

Years of a fierce competition have naturally selected the fittest deep learning algorithms. Yet, although these models work well in practice, we still lack a proper characterization of why they do so. This poses serious questions about the robustness, trus ...

EPFL2023

Explainability as fig leaf? An exploration of experts’ ethical expectations towards machine learning in psychiatry

The increasing implementation of programs supported by machine learning in medical contexts will affect psychiatry. It is crucial to accompany this development with careful ethical considerations informed by empirical research involving experts from the fi ...

2023

Are engineering teachers ready to leverage the power of play to teach transversal skills?

Roland John Tormey, Siara Ruth Isaac, Jessica Elke Dehler Zufferey, Yousef Jalali, Natascia Petringa

What conceptions do teachers hold about learning activities to develop students’ transversal skills? This qualitative exploration at a research-intensive engineering school draws on interviews and focus groups to explore teachers’ ideas about developing in ...

2023

Les Cahiers de l'Ibois 3 / Ibois Notebook 3

Petras Vestartas, Sandra Vuilleumier

Before the twentieth century and concrete modernity, it was stone that embodied the “well built”. Could sustainable wood one day replace concrete as the archetypal material? Will it find a place on the scale of values that gives archi- tecture its referenc ...

EPFL PRESS2022

Textual Explanations and Critiques in Recommendation Systems

Diego Matteo Antognini

Artificial intelligence and machine learning algorithms have become ubiquitous. Although they offer a wide range of benefits, their adoption in decision-critical fields is limited by their lack of interpretability, particularly with textual data. Moreover, ...

EPFL2022

Tracing Embodied Narratives of Critical Thinking

Aditi Kothiyal, Shitanshu Mishra

Critical Thinking (CrT) is generally characterized as an abstract thinking process, detached from the (bodily) actions one engages in during the process. Though recent cognitive theories assert that all thinking is action-based, the embodied and distribute ...

SPRINGER INTERNATIONAL PUBLISHING AG2021

Developing STEM and Team-working Skills Through Collaborative Space Robotics Missions

Francesco Mondada, Evgeniia Bonnet

Building on the success of the first North-South cross-continental collaborative educational robotics mission held in November 2015 [1], this paper presents a practical model for scaling the event up into a program for developing countries, particularly th ...

IEEE2021

Promoting Critical and Design Thinking Activities to Tackle Sustainable Development Goals in Higher Education

Denis Gillet, Isabelle Barbara Marie-Hélène Cardia

Since 2016, the 17 Sustainable Development Goals (SDGs) came into force, and for the first time they include higher education. Therefore, higher institutions are finding ways to incorporate them into their teachings and research activities. This paper cont ...

IEEE2021

How to detect and reduce potential sources of biases in studies of SARS-CoV-2 and COVID-19

Mats Julius Stensrud

In response to the coronavirus disease (COVID-19) pandemic, public health scientists have produced a large and rapidly expanding body of literature that aims to answer critical questions, such as the proportion of the population in a geographic area that h ...

2021

Conversational Multi-Hop Reasoning with Neural Commonsense Knowledge and Symbolic Logic Rules

Antoine Bosselut, Forough Arabshahi

One of the challenges faced by conversational agents is their inability to identify unstated presumptions of their users' commands, a task trivial for humans due to their common sense. In this paper, we propose a zeroshot commonsense reasoning system for c ...

ASSOC COMPUTATIONAL LINGUISTICS-ACL2021

Page 2 sur 3