-
methodological advancements for the deep learning analysis of spectroscopy signals and focus on metabolic biomarkers of interest for psychiatric disorders. The thesis will be carried out mainly at the CREATIS
-
and motor learning. How the deep cerebellar nuclei (CN, the sole output of the cerebellum) integrate sensorimotor information and contribute to the learning and execution of fine movements is not well
-
also to experimentally verify the designs with collaborators in Bordeaux through a running ANR project ("AIM", 2023-2027). The candidate should be familiar with deep learning techniques and / or physics
-
implement cognitive attention models for computer vision adapted to event data. A first step will be to study the state-of-the-art attentional mechanisms in deep networks and their link with cognitive
-
friendly refrigeration [1]. To do so, this PhD aims to develop original modeling methods, based on the development of Machine Learning tools, allowing for the description of complex molecular systems
-
computer science background with an interest in applied mathematics or a strong mathematical background with some knowledge in deep learning and Python+Pytorch. As the goal of the project is to propose novel
-
the Subatech team is one of the pioneers, to control associated errors and biases. Similarly, we will continue exploring innovative deep learning methods emerging from pioneering work within this team
-
on AUTOMATICS, SIGNAL, IMAGES, SPEECH, COGNITION, ROBOTICS and LEARNING. Multidisciplinary and at the interface between the human, the physical and digital worlds, our research is confronted with measurements
-
, and can only be done by combining approaches from different disciplines (lithic technology, geometric morphometry, deep learning). Candidate's tasks The candidate will first develop a suitable
-
modeling and deep learning algorithms that will integrate optical and radar images from the Copernicus program (Sentinel-1 and Sentinel-2), as well as in-situ measurements, in order to make accurate