BEGIN:VCALENDAR VERSION:2.0 PRODID:-//Vrije Universiteit Amsterdam//NONSGML v1.0//EN NAME:PhD defence L.P. Silvestrin METHOD:PUBLISH BEGIN:VEVENT DTSTART:20260513T134500 DTEND:20260513T151500 DTSTAMP:20260513T134500 UID:phd-defence-l-p-silvestrin@8F96275E-9F55-4B3F-A143-836282E12573 CREATED:20260826T200940 LOCATION: SUMMARY:PhD defence L.P. Silvestrin X-ALT-DESC;FMTTYPE=text/html:

Efficient Machine Le arning for Time-Varying Data

Research makes AI more relia ble with changing data

In practice , this type of data changes constantly. Sensors are adjusted, conditi ons fluctuate, and important signals, such as malfunctions or medical complications, often occur only rarely. According to Silvestrin, sta ndard machine learning methods frequently fall short as a result. The y implicitly assume that data remains stable, whereas in reality, thi s is rarely the case.

The research shows that usable prediction s do remain possible, provided that algorithms explicitly take this v ariability into account. Silvestrin developed techniques that handle limited and evolving datasets better. These methods proved effective in industrial applications and healthcare, among others.

Fewer malfunctions and better care decisions

The soc ietal impact of these findings could be significant. In industry, com panies can use the new approach to detect anomalies in machines earli er, even before malfunctions occur. This saves costs and prevents dow ntime. A concrete example is a warning system for overheating motors in conveyor belts. The new methods help ensure that rare problems are not missed, while simultaneously limiting the number of false alarms .

This also offers opportunities in hospitals. Doctors often ha ve to make decisions based on limited and constantly changing patient data. The new techniques can, for example, assist in determining the right moment to remove a breathing tube in the intensive care unit, even when little new data is available.

AI that moves w ith reality

The core of the research is that artificia l intelligence works better when systems adapt to change, rather than assuming a stable world. This is relevant in a time when more and mo re decisions depend on data that is incomplete, noise-sensitive, and dynamic.

Some applications of the new methods are already immed iately deployable because they have been tested in realistic environm ents. However, further validation is required for broader application , depending on the specific sector. The research thus aligns with lar ger societal developments, such as the rise of smart healthcare syste ms, a more reliable industry, and the growing role of AI in complex, realistic situations.

More information on the thesis

DESCRIPTION: Efficient Machine Learning for Time-Varying Data

Rese arch makes AI more reliable with changing data

Machine learning c an handle changing and incomplete data much better than previously as sumed. This is evident from research by data scientist Luis Silvestri n, who developed new methods to analyze time series of sensor data - such as measurements from machines or medical equipment - more reliab ly.In practice, this type of data changes constantly. Sensors are adj usted, conditions fluctuate, and important signals, such as malfuncti ons or medical complications, often occur only rarely. According to S ilvestrin, standard machine learning methods frequently fall short as a result. They implicitly assume that data remains stable, whereas i n reality, this is rarely the case.The research shows that usable pre dictions do remain possible, provided that algorithms explicitly take this variability into account. Silvestrin developed techniques that handle limited and evolving datasets better. These methods proved eff ective in industrial applications and healthcare, among others.Fewer malfunctions and better care decisionsThe societal i mpact of these findings could be significant. In industry, companies can use the new approach to detect anomalies in machines earlier, eve n before malfunctions occur. This saves costs and prevents downtime. A concrete example is a warning system for overheating motors in conv eyor belts. The new methods help ensure that rare problems are not mi ssed, while simultaneously limiting the number of false alarms.This a lso offers opportunities in hospitals. Doctors often have to make dec isions based on limited and constantly changing patient data. The new techniques can, for example, assist in determining the right moment to remove a breathing tube in the intensive care unit, even when litt le new data is available.AI that moves with realityT he core of the research is that artificial intelligence works better when systems adapt to change, rather than assuming a stable world. Th is is relevant in a time when more and more decisions depend on data that is incomplete, noise-sensitive, and dynamic.Some applications of the new methods are already immediately deployable because they have been tested in realistic environments. However, further validation i s required for broader application, depending on the specific sector. The research thus aligns with larger societal developments, such as the rise of smart healthcare systems, a more reliable industry, and t he growing role of AI in complex, realistic situations.More informati on on the thesis END:VEVENT END:VCALENDAR