Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.
DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.
This thesis focuses on two selected learning problems: 1) statistical inference on graphs models, and, 2) gradient descent on neural networks, with the common objective of defining and analysing the measures that characterize the fundamental limits.In the ...
The laboratory ALICE (Atelier de la Conception de l’Espace) at the École Polytechnique Fédérale de Lausanne (EPFL) advances a comprehensive approach to data-based drawing oriented towards architectural and urban co-design processes. This drawing methodolog ...
In this dissertation, we propose multiple methods to improve transfer learning for pretrained language models (PLMs). Broadly, transfer learning is a powerful technique in natural language processing, where a language model is first pre-trained on a data-r ...
It is well established that surface topography can affect cell functions. However, finding a reproducible and reliable method for regulating stem cell behavior is still under investigation. It has been shown that cell imprinted substrates contain micro- an ...
Here, we show that, in the developing spinal cord, after the early Wnt-mediated Tcf transcription activation that confers dorsal identity to neural stem cells, neurogenesis redirects beta-catenin from the adherens junctions to the nucleus to stimulate Tcfo ...
Knowledge of a program's input format is essential for effective input generation in fuzzing. Automated input format reverse engineering represents an attractive but challenging approach to learning the format. In this paper, we address several challenges ...
Hyperdimensional (HD) computing is a novel approach to machine learning inspired by neuroscience, which uses vectors in a hyper-dimensional space to represent data and models. This approach has gained significant interest in recent years with applications ...
On the one hand, the web needs to be secured from malicious activities such as bots or DoS attacks; on the other hand, such needs ideally should not justify services tracking people's activities on the web. Anonymous tokens provide a nice tradeoff between ...
Information collected through sensor measurements has the potential to improve knowledge of complex-system behavior, leading to better decisions related to system management. In this situation, and particularly when using digital twins, the quality of sens ...
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 ...
