Essays about: "Djupt Lärande"

Showing result 1 - 5 of 19 essays containing the words Djupt Lärande.

1. 1. Förundrad av fysik? : En fenomenologisk studie kring högstadieelevers upplevelser av förundran som epistemisk känsla i fysikundervisningen

   University essay from KTH/Skolan för industriell teknik och management (ITM)

   Author : Daniel Stoor; [2023]
   Keywords : science education; physics; lower secondary school; epistemic emotions; phenomenology; wonder; Naturvetenskapsundervisning; fysik; högstadiet; epistemiska känslor; fenomenologi; förundran;

   Abstract : Naturvetenskapsundervisning idag tenderar att måla en bild av att allt redan är förklarat och alla samband är upptäckta inom naturvetenskap. Skolans jobb handlar bara om att lära ut alla förklaringarna. READ MORE

3. 2. An Industrial Application of Semi-supervised techniques for automatic surface inspection of stainless steel. : Are pseudo-labeling and consistency regularization effective in a real industrial context?

   University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Author : Mattia Zoffoli; [2022]
   Keywords : Deep Learning; Computer Vision; Semi-Supervised Learning; Automatic Inspection; Stainless Steel; Djupt lärande; datorseende; Semi-övervakat lärande; Automatisk inspektion; Rostfritt stål;

   Abstract : Recent developments in the field of Semi-Supervised Learning are working to avoid the bottleneck of data labeling. This can be achieved by leveraging unlabeled data to limit the amount of labeled data needed for training deep learning models. READ MORE

4. 3. Privacy leaks from deep linear networks : Information leak via shared gradients in federated learning systems

   University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Author : Guangze Shi; [2022]
   Keywords : Federated learning; Gradient share; Deep neural network; Information leak; Privacy and security; Maskininlärning med flera noder; Gradientdelning; Djupt neuralt nätverk; Informationsläcka; Integritetssäkerhet;

   Abstract : The field of Artificial Intelligence (AI) has always faced two major challenges. The first is that data is kept scattered and cannot be collected for more efficiently use. The second is that data privacy and security need to be continuously strengthened. READ MORE

5. 4. Research on Dynamic Offloading Strategy of Satellite Edge Computing Based on Deep Reinforcement Learning

   University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Author : Rui Geng; [2021]
   Keywords : Deep reinforcement learning; Satellite edge computing; Offloading strategy; Djup Förstärkning Lärande; Satellit Kant Datoranvändning; Avlastning Strategi;

   Abstract : Nowadays more and more data is generated at the edge of the network, and people are beginning to consider decentralizing computing tasks to the edge of the network. The network architecture of edge computing is different from the traditional network architecture. READ MORE

6. 5. Deep Reinforcement Learning for Autonomous Highway Driving Scenario

   University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Author : Neil Pradhan; [2021]
   Keywords : Deep reinforcement learning; Highway driving scenario; Tactical decision making; fuel reduction; high-level decision making; autonomous driving; Partially Observable Markov Decision Process POMDP .; Lärande om djupförstärkning; motorvägsscenario; taktiskt beslutsfattande; bränslereduktion; beslut på hög nivå; autonom körning; Partially Observable Markov Decision Process POMDP ;

   Abstract : We present an autonomous driving agent on a simulated highway driving scenario with vehicles such as cars and trucks moving with stochastically variable velocity profiles. The focus of the simulated environment is to test tactical decision making in highway driving scenarios. READ MORE