Zobrazeno 1 - 10
of 1 351
pro vyhledávání: '"Inlärning"'
Autor:
Neuman, Erica
To be able to make accurate predictions and adapt, we sometimes need to adjust our understanding of the world, yet what incentivizes expansion of our mental world models remains poorly understood. The aim of this study was to investigate what motivat
Externí odkaz:
http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-227494
Autor:
Maus, Rickard
Multi-object tracking is a classic engineering problem wherein a system must keep track of the identities of a set of a priori unknown objects through a sequence, for example video. Perfect execution of this task would mean no spurious or missed dete
Externí odkaz:
http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-346209
Autor:
El Yaacoub, Khalid
Emerging machine learning (ML) techniques are showing great potential in prediction performance. However, research and development is often conducted in an environment with extensive computational resources and blinded by prediction performance. In r
Externí odkaz:
http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-344747
Autor:
Stojanovski, Kristofer
Syftet med följande arbete var att skapa en kunskapsöversikt om hur gymnasieelevers prestationer påverkas i matematikämnet när digitala verktyg är närvarande i undervisningen. Termen prestation används som ett samlingsbegrepp för elevernas m
Externí odkaz:
http://urn.kb.se/resolve?urn=urn:nbn:se:mau:diva-65515
The purpose of this qualitative study is to compare five teachers’ beliefs about their students’ learning of vocabulary and compare that with current theories and recommended practices in the field. The method for collecting data was semi-structu
Externí odkaz:
http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-218752
Autor:
Norrthon, Alice, Schörling, Emelie
Quality education is one of the United Nations Sustainable Development Goals. In pursuit of reaching this goal there are multiple available techniques today, where one of them is Artificial Intelligence, AI. How it can be used is not established but
Externí odkaz:
http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-330997
Autor:
Carp, Amanda
In the domain of cyber security, machine learning promises advanced threat detection. However, the volume of available unlabeled data poses challenges for efficient data management. This study investigates the potential for active learning, a subset
Externí odkaz:
http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-336621
Autor:
Caliò, Filippo
Clustering keywords is an important Natural Language Processing task that can be adopted by several businesses since it helps to organize and group related keywords together. By clustering keywords, businesses can better understand the topics their c
Externí odkaz:
http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-338333
In many relevant scenarios, there is an imbalance between abundant unlabeled data and scarce labeled data to train predictive models. Semi-Supervised Learning and Active Learning are two distinct approaches to deal with this issue. The first one dire
Externí odkaz:
http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-196140