Probing transfer learning with a model of synthetic correlated datasets

Chat with Graph Search

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.

Measuring animal behaviors is a crucial task in a range of scientific applications. Modern approaches with deep neural networks calls for developing solutions that solve a wide range of vision and language tasks. This ubiquitous need for understanding beha ...

Deep Generative Models (DGMs) have rapidly advanced in recent years, becoming essential tools in various fields due to their ability to learn data distributions and generate synthetic data. Their importance in transportation research is increasingly recogn ...

Diffusion Magnetic Resonance Imaging (dMRI) is a non-invasive method for depicting brain microstructure in vivo. Fiber orientation distributions (FODs) are mathematical representations extensively used to map white matter fiber configurations. Recently, FO ...

Microscopy is one of the essential tools to quantify and advance our understanding of living systems. Modern digital microscopes enable measurements at unprecedented spatiotemporal scale, so automated processing methods are required to complete tasks such ...

In recent years, exploring deep generative models for generating time series has garnered significant interest within the research community. These models have found wide-ranging applications in areas such as data augmentation, scenario simulation, and the ...

This repository contains microphysics routines, scripts, and processed data from the Weather Research and Forecasting (WRF) model simulations presented in the paper "RaFSIP: Parameterizing ice multiplication in models using a machine learning approach", by ...

Recently, there has been an arms race of pose forecasting methods aimed at solving the spatio-temporal task of predicting a sequence of future 3D poses of a person given a sequence of past observed ones. However, the lack of unified benchmarks and limited ...

This research introduces an innovative framework to engineering design to tackle the challenges of robustness against manufacturing deviations and holistic optimization simultaneously in a multi-disciplinary, multi-subsystems context. The methodology is ba ...

Data-driven approaches have been applied to reduce the cost of accurate computational studies on materials, by using only a small number of expensive reference electronic structure calculations for a representative subset of the materials space, and using ...

Electrochemical CO2 reduction (eCO(2)R) is a promising strategy to transform detrimental CO2 emissions into sustainable fuels and chemicals. Key requirements for advancing this field are the development of analytical systems and of methods that are able to ...

In this thesis, we explore techniques for addressing the communication bottleneck in data-parallel distributed training of deep learning models. We investigate algorithms that either reduce the size of the messages that are exchanged between workers, or th ...

Magnetic resonance imaging (MRI) is a valuable tool for studying subcutaneous implants in rodents, providing non-invasive insight into biomaterial conformability and longitudinal characterization. However, considerable variability in existing image analysi ...

Epilepsy is one of the most prevalent brain disorders that disrupts the lives of millions worldwide. For patients with drug-resistant seizures, there exist implantable devices capable of monitoring neural activity, promptly triggering neurostimulation to r ...

We propose a physics-informed message-passing graph neural network (GNN) for learning the dynamics of springmass systems. The proposed method embeds the underlying physics directly into the message-passing scheme of the GNN. We compare the new scheme with ...

Compute memories are memory arrays augmented with dedicated logic to support arithmetic. They support the efficient execution of data-centric computing patterns, such as those characterizing Artificial Intelligence (AI) algorithms. These architectures can ...

This thesis consists of three applications of machine learning techniques to empirical asset pricing. In the first part, which is co-authored work with Oksana Bashchenko, we develop a new method that detects jumps nonparametrically in financial time series ...

In digital imaging, especially in the process of data acquisition and transmission, images are often affected by impulsive noise. Therefore, it is essential to remove impulsive noise from images before any further processing. Due to the remarkable performa ...

The amount of study on Quantum Machine Learning (QML) is increasing extensively due to its potential advantages in terms of representational power and computational resources. These advances suggest a possibility to extend its usage into the context of Ear ...

Convolutional neural networks (CNNs) represent the new reference approach for semantic segmentation of very-high-resolution (VHR) images, due to their ability to automatically capture semantic information while learning relevant features. However, as for m ...

Li-S batteries are a promising alternative to Li-ion batteries, offering large energy storage capacity and wide operating temperature range. However, their performance is heavily affected by the Li-polysulfide (LiPS) shuttling. Computational screening of L ...

Probing transfer learning with a model of synthetic correlated datasets

Chat with Graph Search

Neuroscience-inspired computer vision and language modeling for behavior analysis

A gentle introduction and tutorial on Deep Generative Models in transportation research

Ground-Truth Effects in Learning-Based Fiber Orientation Distribution Estimation in Neonatal Brains

Label-Efficient Deep Learning Methods for Event Detection, Object Segmentation and Cell Tracking in Biological Microscopy Images

One-Pass Generation of Multivariate Time Series through Conditional Multivariate Modeling

Data and scripts for the RaFSIP scheme

Toward Reliable Human Pose Forecasting With Uncertainty

An Integrated Approach to Designing Robust Gas-Bearing Supported Turbocompressors through Surrogate Modeling and Constrained All-At-Once Multi-Objective Optimization

Efficient and insightful descriptors for representing molecular and material space

Parallel experiments in electrochemical CO2 reduction enabled by standardized analytics

Communication-efficient distributed training of machine learning models

Automated segmentation and labeling of subcutaneous mouse implants at 14.1T

Enhancing Epileptic Seizure Detection with EEG Feature Embeddings

Learning Dynamics of Spring-Mass Models with Physics-Informed Graph Neural Networks

Overflow-free compute memories for edge AI acceleration

Essays in Empirical Asset Pricing

Impulsive noise removal via a blind CNN enhanced by an iterative post-processing

Quantum Convolutional Circuits For Earth Observation Image Classification

A Semisupervised CRF Model for CNN-Based Semantic Segmentation With Sparse Ground Truth

Accelerating the theoretical study of Li-polysulfide adsorption on single-atom catalysts via machine learning approaches