Non-invasive ventilation (NIV) is recognised as an effective treatment for chronic
hypercapnic respiratory failure. Monitoring NIV during sleep may be preferable to daytime …

Compared with invasive ventilation, non-invasive ventilation (NIV) has two unique
characteristics: the non-hermetic nature of the system and the fact that the ventilator-lung …

While machine learning is going through an era of celebrated success, concerns have been
raised about the vulnerability of its backbone: stochastic gradient descent (SGD). Recent …

Objective: To compare compliance with and effectiveness of adaptive servoventilation (ASV)
versus continuous positive airway pressure (CPAP) in patients with the central sleep apnoea …

While machine learning is going through an era of celebrated success, concerns have been
raised about the vulnerability of its backbone: stochastic gradient descent (SGD). Recent …

We present AGGREGATHOR, a framework that implements state-of-the-art robust
(Byzantine-resilient) distributed stochastic gradient descent. Following the standard …

Many medical or surgical interventions can benefit from the use of computers. Through
progress of technology and growing consciousness of the possibilities of real clinical …

Abstract Byzantine-resilient Stochastic Gradient Descent (SGD) aims at shielding model
training from Byzantine faults, be they ill-labeled training datapoints, exploited …

We study\emph {Byzantine collaborative learning}, where $ n $ nodes seek to collectively
learn from each others' local data. The data distribution may vary from one node to another …

Machine Learning (ML) solutions are nowadays distributed, according to the so-called
server/worker architecture. One server holds the model parameters while several workers …