Concept
Formation à distance
Publications associées (148)
Imitation Learning in Discounted Linear MDPs without exploration assumptions
Volkan Cevher, Efstratios Panteleimon Skoulakis, Luca Viano
We present a new algorithm for imitation learning in infinite horizon linear MDPs dubbed ILARL which greatly improves the bound on the number of trajectories that the learner needs to sample from the environment. In particular, we re- move exploration assu ...
2024Revisiting adversarial training for the worst-performing class
Volkan Cevher, Grigorios Chrysos, Thomas Michaelsen Pethick
Despite progress in adversarial training (AT), there is a substantial gap between the topperforming and worst-performing classes in many datasets. For example, on CIFAR10, the accuracies for the best and worst classes are 74% and 23%, respectively. We argu ...
2023Finding Paths for Explainable MOOC Recommendation: A Learner Perspective
Jibril Albachir Frej, Tatjana Nazaretsky
The increasing availability of Massive Open Online Courses (MOOCs) has created a necessity for personalized course recommendation systems. These systems often combine neural networks with Knowledge Graphs (KGs) to achieve richer representations of learners ...
2023Supporting Teachers' Orchestration in Robot-mediated Classrooms
To bring educational robots to classrooms, we need to consider teachers' self-efficacy and challenges in managing a robot-mediated classroom, and how to support them in overcoming these challenges. Orchestration tools are designed to support teachers by pr ...
EPFL2023Million-scale data integrated deep neural network for phonon properties of heuslers spanning the periodic table
Changpeng Lin, Hong Zhang, Chen Shen, Yong Zhao
Existing machine learning potentials for predicting phonon properties of crystals are typically limited on a material-to-material basis, primarily due to the exponential scaling of model complexity with the number of atomic species. We address this bottlen ...
NATURE PORTFOLIO2023A dynamic attractor network model of memory formation, reinforcement and forgetting
Wulfram Gerstner, Chiara Gastaldi, Marta Boscaglia
Empirical evidence shows that memories that are frequently revisited are easy to recall, and that familiar items involve larger hippocampal representations than less familiar ones. In line with these observations, here we develop a modelling approach to pr ...
San Francisco2023Meta Transfer Learning for Early Success Prediction in MOOCs
Despite the increasing popularity of massive open online courses (MOOCs), many suffer from high dropout and low success rates. Early prediction of student success for targeted intervention is therefore essential to ensure no student is left behind in a cou ...
ACM2022