Zobrazeno 1 - 10
of 451
pro vyhledávání: '"Djupinlärning"'
Autor:
Richard Pleijel
Publikováno v:
Högre Utbildning, Vol 11, Iss 1, Pp 16-26 (2021)
I denna artikel diskuteras begreppen ytinlärning och djupinlärning. Artikeln syftar till en kritisk granskning av hur dessa två begrepp präglar olika sätt att tala om lärande, främst i en samtida, praktiskt orienterad högskolepedagogisk konte
Externí odkaz:
https://doaj.org/article/2dc18f83d08e4ab9bb7b2acd297db0dd
Autor:
Gauriye, Samuel
Artificiell intelligens (AI) är en maskins förmåga att visa människoliknande egenskaper såsom inlärning, problemlösning, planering och kreativitet. Genom att använda stora datamängder och avancerade algoritmer kan AI-system lära sig att utf
Externí odkaz:
http://urn.kb.se/resolve?urn=urn:nbn:se:his:diva-24078
In the field of video surveillance, vast amounts of data are gathered each day. To be able to identify what occurred during a recorded session, a human annotator has to go through the footage and annotate the different events. This is a tedious and e
Externí odkaz:
http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-205662
Deep Q-Learning for Lane Localization : Exploring Reinforcement Learning for Accurate Lane Detection
Autor:
Ganesan, Aishwarya
In autonomous driving, achieving fast and reliable lane detection is essential. This project explores a two-step lane detection and localization approach, diverging from relying solely on end-to-end deep learning methods, which often struggle with cu
Externí odkaz:
http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-346213
Autor:
Rolf Lidskog
Publikováno v:
Sociologisk Forskning, Vol 57, Iss 2 (2020)
Artificial intelligence (AI) is a growing social phenomenon, both as a technical infrastructure and as a sociotechnical imaginary. While there is ample sociological research on AI’s implications for different societal sectors, there has been limite
Externí odkaz:
https://doaj.org/article/b6f3494a23054c3dbefa7e1829a086c6
Autor:
Dagur Guðmundsson, Árni
Modern deep neural networks do not produce well calibrated estimates of their own uncertainty, unless specific uncertainty estimation techniques are applied. Common uncertainty estimation techniques such as Deep Ensembles and Monte Carlo Dropout nece
Externí odkaz:
http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-344381
Autor:
Nilsson, Alfred
This thesis introduces an novel approach to model regularization in Vision Transformers (ViTs), a category of deep learning models. It employs stochastic embedded feature selection within the context of echocardiography video analysis, specifically f
Externí odkaz:
http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-344291
Autor:
Rey, Robert
The focus of this work is the task of 3D human pose estimation, more specifically by making use of key points located in single monocular images in order to estimate the location of human body joints in a 3D space. It was done in association with Tra
Externí odkaz:
http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-344247