Avancerad sökning

Hittade 2 uppsatser som matchar ovanstående sökkriterier.

1. 1. Recursive knowledge representation for multi-agent games over graphs

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Gustaf Pihl; [2022]
   Nyckelord :MKBSC; KBSC; MAGIIAN; Game Theory; Strategy Synthesis; Knowledge Representation; Epistemic Knowledge; Common Knowledge; MKBSC; KBSC; MAGIIAN; Spelteori; Strategisyntes; Kunskapsrepresentation; Epistemologi; Gemensam kunskap;

   Sammanfattning : In this thesis I explore a construction for Multi-Agent Games of Imperfect Information Against Nature (MAGIIAN) introduced by Gurov et al. called the Multiplayer Knowledge-Based Subset Construction (MKBSC). LÄS MER

3. 2. Prediction of training time for deep neural networks in TensorFlow

   Kandidat-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Jacob Adlers; Gustaf Pihl; [2018]
   Nyckelord :Machine Learning; TensorFlow;

   Sammanfattning : Machine learning has gained a lot of interest over the past years and is now used extensively in various areas. Google has developed a framework called TensorFlow which simplifies the usage of machine learning without compromising the end result. However, it does not resolve the issue of neural network training being time consuming. LÄS MER