Federated Learning: Issues in Medical Application

29 de May de 2022 9 de January de 2022

In this presentation, the current issues to make federated learning flawlessly useful in the real world will be briefly overviewed. They are related to data/system heterogeneity, client management, traceability, and security. Also, we introduce the modularized federated learning framework, we currently develop, to experiment various techniques and protocols to find solutions for aforementioned issues. The framework will be open to public after development completes.

Pages: 1 2 3

Model-based Decision Making with Imagination for Autonomous Parking

10 de October de 2021 27 de August de 2021

Autonomous parking technology is a key concept within autonomous driving research. This paper will propose an imaginative autonomous parking algorithm to solve issues concerned with parking.

Pages: 1 2 3

Fourier Neural Operator for Parametric Partial Differential Equations

29 de October de 2020 11 de November de 2020

The classical development of neural networks has primarily focused on learning mappings between finite-dimensional Euclidean spaces. Recently, this has been generalized to neural operators that learn mappings between function spaces. For partial differential equations (PDEs), neural operators directly learn the mapping from any functional parametric dependence to the solution.

Pages: 1 2 3

Composing AI Pipelines with AI4EU Experiments

15 de June de 2020 15 de June de 2020

Show how to onboard AI tools as re-usable building blocks that then can be used to easily compose AI pipelines in the AI4EU Experiments visual editor

Pages: 1 2

Data Ethics in Public Procurement of AI-based Services and Solutions

2 de June de 2020 2 de June de 2020

Technologies are not neutral, neither are choices in the public procurement of AI. The AI systems we deploy today are the systems we will live with tomorrow.

Pages: 1 2 3

A socio-technical framework for digital contact tracing

22 de May de 2020 22 de May de 2020

In their efforts to tackle the COVID-19 crisis, decision makers are considering the development and use of smartphone applications for contact tracing. Even though these applications differ in technology and methods, there is an increasing concern about their implications for privacy and human rights. Here we propose a framework to evaluate their suitability in terms of impact on the users, employed technology and governance methods.

Pages: 1 2 3

Toolbox for the use of technology and data to combat COVID-19: mobile applications and the use of anonymised mobility data

11 de April de 2020 11 de April de 2020

This recommendation sets up a process for developing a common approach, referred to as a Toolbox, to use digital means to address the crisis. The Toolbox will consist of practical measures for making effective use of technologies and data, with a focus on two areas

Keras Succinctly

12 de March de 2020 12 de March de 2020

Neural networks are a powerful tool for developers, but harnessing them can be a challenge. With Keras Succinctly, author James McCaffrey introduces Keras, an open-source, neural network library designed specifically to make working with backend neural network tools easier.

Pages: 1 2 3

Frameworks (Article)