Show all
Show all

Title Description Supervisors Status
Manifold learning applications on graphs and videos Background: Representation learning of both structured and graph data is mostly performed in Euclidean space. Earlier studies have shed light … Ali Hariri Available
Short-term precipitation forecasting using Lagrangian Convolutional Neural Networks Background The high-resolution short-range forecasting (0–6h ahead) of precipitation (nowcasting) is an essential component of severe weather and hydrological early … Gionata Ghiggi, Daniele Grattarola Available
Short-term precipitation forecasting over Switzerland using Conditional Generative Adversarial Networks. Background The high-resolution short-range forecasting (0–6h ahead) of precipitation (nowcasting) is an essential component of severe weather and hydrological early … Gionata Ghiggi, Daniele Grattarola Available
A Generalized Representation of Chemical Entities for Machine Learning Tasks What's it about. Machine learning on big chemical data has recently produced intriguing results and was shown to be capable … Daniel Probst Available
Development, assessment and optimization of an Active Nonlinear Electroacoustic Resonator Acoustic metamaterials (AMMs) and metasurfaces (AMSs) are engineered structures aimed at achieving unprecedented acoustic properties not available in nature. They … Xinxin Guo Available
Exploring Implicit Neural Representations from a Signal Processing Perspective Background. Implicit neural representations (INRs) have recently emerged as a powerful way of representing signals using neural networks. INRs are … Daniele Grattarola Assigned
Adaptive Neural Cellular Automata Background: Neural Cellular Automata (NCA) are a class of cellular automata that use neural networks as learnable transition rules. By … Daniele Grattarola Assigned
Adaptive geometric neural networks Background: Networks are powerful mathematical objects which are widely used to model systems composed of interacting constituents such as those … Adám Gosztolai Assigned
Traffic noise Radar: Tracking and estimation of individual vehicle noise emission Traffic noise and its effects on health has become increasingly more relevant these days. The latest noise emission model, SonRoad18, … Thach Pham Vu Assigned
Granular synthesis applied to car sound design Granular synthesis is an alternative to conventional sound synthesis (additive, substractive or frequency modulation, among others), not relying on manipulating … Thach Pham Vu, Vincent Grimaldi Assigned
Controlling the timbre of wind instruments with active impedance control A wind instrument can generally be assimilated to a axisymmetric hollow duct, with varying (or constant) cross-section along the main … Maxime Volery Assigned
Development of a plasma sound absorber Plasma technology can be used for sound diffusion without resorting to a vibrating membrane and a cumbersome driver (as in … Stanislav Sergeev Finished
Graph Neural Networks applied to team sports Project Description Team sports rely on highly tactical and complex strategies often suggested by coaching staffs. For instance, basketball is … Ali Hariri Finished
Machine learning for urban traffic classification In Switzerland, more than 1 million people are concerned with traffic noise, which may have many adverse effects on health. … Hervé Lissek Finished
Heterogeneous Message Passing Neural Network for Semi-Supervised Learning Task Node attribute completion in knowledge graphs. Description In recent years, only a few graph representation learning (GRL) approaches have … Eda Bayram Finished
Development of a high performance plasma-based actuator for active noise reduction The development of novel noise reduction technologies is challenged by the growing environmental noise pollution concerns. Since conventional passive noise … Stanislav Sergeev Finished
Anomaly detection on large scale distributed sensors, combining signal processing and machine learning This project may be done as a company internship for a master student, for the summer 2021 instead of a … Benjamin Ricaud Finished
Deep Learning on Neuronal Morphologies Project description at https://www.epfl.ch/research/domains/bluebrain/deep-learning-on-neuronal-morphologies-internship/. Michaël Defferrard, Lida Kanari, Francesco Casalegno, Stanislav Schmidt Finished
Is my deep neural network good at memorizing? Project Description How much information have deep neural network weights memorized after training? One way of answering this question is … Konstantinos Pitas Finished
How flat is my minimum? Project Description Predicting how a deep neural network will perform on new datapoints after training is important in real applications. … Konstantinos Pitas Finished
Better Uncertainty Estimates for DNNs v2! Project Description Deriving uncertainty estimates for feedforward DNN predictions is critical in a number of tasks. For example you might … Konstantinos Pitas Finished
Room modes identification and characterization and its potential application Room modes can significantly impair the quality of sound diffusion, in particular at low-frequencies and in small auditoria. These low-frequency … Thach Pham Vu Finished
Development of a microphone array to track mobile noise sources Microphone arrays can be used to locate and track moving sound sources, thanks to advanced signal processing techniques. Such techniques … Benjamin Ricaud, Hervé Lissek Finished
Multi-actuated panel for active sound absorption The distributed mode loudspeaker (DML) technology is a flat panel loudspeaker from which sound is generated a set of electromechanical … Hervé Lissek Finished
Implementation of a low-cost real-time reverberation algorithm The LTS2-Acoustics is working on binaural audio synthesis for applications in hearing aid technologies. Our activities deal with the improvement … Vincent Grimaldi Finished