Nettsider med emneord «machine learning»

Publisert 22. sep. 2015 10:18
Publisert 2. okt. 2012 10:40

 

The use of lexical semantic information for the task of syntactic parsing has seen varied success. Recently, however, the use of lexical semantic clusters derived from large corpora has been shown to improve parsing performance. It is still unclear, however, how different properties of these clusters affect results. This project aims to investigate the use of different types of clusters during syntactic parsing. 

More precisely the idea is to use word clusters as a source for features in a statistical disambiguation model for a dependency parser. Generally, the clusters will group together words with similar distributional properties. The exact nature of these similarity relations, however, will vary depending on the types of context features that are used when performing the clustering. For this project we will basically be doing an extrinsic form of cluster evaluation then; investigating how different clustering parameters in turn affect the performance of a statistical parser. 

Publisert 25. jan. 2019 08:55

Water flow on, in and under glaciers still remains a poorly understood system. Water can flow over the surface of glaciers, as well as through channels inside and under the ice. The water thereby has strong influence both on ice melt and glacier dynamics, making glacial hydrology an important field of study.

Publisert 25. jan. 2019 08:56

Water flow on, in and under glaciers still remains a poorly understood system. Water can flow over the surface of glaciers, as well as through channels inside and under the ice. The water thereby has strong influence both on ice melt and glacier dynamics, making glacial hydrology an important field of study.

Publisert 31. jan. 2019 09:54

Christos Dimitrakakis talks about the challenge of identity protection.

Publisert 11. apr. 2019 15:19

João Gama, Associate Professor at the University of Porto, talks about the limitations of current machine learning and data mining algorithms in dealing with real-time data.

Publisert 2. okt. 2019 09:38

Water flow on, in and under glaciers still remains a poorly understood system. Water can flow over the surface of glaciers, as well as through channels inside and under the ice. The water thereby has strong influence both on ice melt and glacier dynamics, making glacial hydrology an important field of study.

Publisert 15. mars 2021 14:22

Model independent searches for new physics are proposed as a way to be sensitive to various scenarios of new physics theories in final states with e.g. leptons recorded with the ATLAS detector.

Publisert 25. feb. 2020 09:17

Classification models are often used to make decisions that affect humans: whether to approve a loan application, extend a job offer, or provide insurance. In such applications, it is desirable for the individuals to not only knowing the results but also have the ability to change the decisions of the model. For example, when a person is denied a loan by a credit scoring model, in addition to know why he/she can not received the loan, it is meaningful for the person to know what he/she can do to influence the decision, i.e. what are the input variables that, if values are changed, can alter the decision of the model. Otherwise, without this information, he/she will be denied the loan as long as the model is deployed, and – more importantly – will lack agency over a decision that affects their livelihood.

Publisert 25. feb. 2020 09:15

Classification models are often used to make decisions that affect humans: whether to approve a loan application, extend a job offer, or provide insurance. In such applications, it is desirable for the individuals to not only knowing the results but also have the ability to change the decisions of the model. For example, when a person is denied a loan by a credit scoring model, in addition to know why he/she can not received the loan, it is meaningful for the person to know what he/she can do to influence the decision, i.e. what are the input variables that, if values are changed, can alter the decision of the model. Otherwise, without this information, he/she will be denied the loan as long as the model is deployed, and – more importantly – will lack agency over a decision that affects their livelihood.

Publisert 5. mars 2021 14:08

Nowadays, Artificial Intelligence (AI) is democratized in our everyday life. Machine Learning (ML) plays a primary role in many AI decision systems, often in ways that are difficult or impossible to understand by human stakeholders. Therefore, explaining the relationship between the input and output of ML models is essential for developing trustworthy decision systems. Explainable Artificial Intelligence (XAI) is a field that aims to create a suite of tools, techniques, and algorithms for interpreting, refining, and validating ML models.

Publisert 24. sep. 2018 10:40
Publisert 31. aug. 2020 11:42

Water flow on, in and under glaciers still remains a poorly understood system. Water can flow over the surface of glaciers, as well as through channels inside and under the ice. The water thereby has a strong influence both on ice melt and glacier dynamics, making glacial hydrology an important field of study.

Publisert 31. aug. 2020 11:45

Water flow on, in and under glaciers still remains a poorly understood system. Water can flow over the surface of glaciers, as well as through channels inside and under the ice. The water thereby has a strong influence both on ice melt and glacier dynamics, making glacial hydrology an important field of study.

Publisert 6. jan. 2020 14:18
photo portrait of a young man, brown hair, blue eyes
Publisert 28. mai 2020 10:01

Martin de los Rios, The ICTP South American Institute for Fundamental Research

Publisert 5. feb. 2020 17:23