Sökning: "decentralized learning"

Visar resultat 1 - 5 av 42 avhandlingar innehållade orden decentralized learning.

1. 1. A study of wireless communications with reinforcement learning

   Författare :Wanlu Lei; Ming Xiao; Chenguang Lu; Mikael Skoglund; Geoffrey Ye Li; KTH; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Reinforcement learning; wireless communications; decentralized learning; beam tracking; machine learning; Förstärkningsinlärning; trådlös kommunikation; decentrali- serad inlärning; strålspårning i mmvåg; maskininlärning; Electrical Engineering; Elektro- och systemteknik;

   Sammanfattning :  The explosive proliferation of mobile users and wireless data traffic in recent years pose imminent challenges upon wireless system design. The trendfor wireless communications becoming more complicated, decentralized andintelligent is inevitable. LÄS MER

3. 2. Towards Decentralized Graph Learning

   Författare :Lodovico Giaretta; Sarunas Girdzijauskas; Henrik Boström; Leila Bahri; Márk Jelasity; KTH; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Informations- och kommunikationsteknik; Information and Communication Technology;

   Sammanfattning : Current Machine Learning (ML) approaches typically present either a centralized or federated architecture. However, these architectures cannot easily keep up with some of the challenges introduced by recent trends, such as the growth in the number of IoT devices, increasing awareness about the privacy and security implications of extensive data collection, and the rise of graph-structured data and Graph Representation Learning. LÄS MER

4. 3. Lärarkunskapens uttryck : en studie av lärares självförståelse och vardagspraktik

   Författare :Anders Magnusson; Linköpings universitet; []
   Nyckelord :SAMHÄLLSVETENSKAP; SOCIAL SCIENCES; SAMHÄLLSVETENSKAP; SOCIAL SCIENCES;

   Sammanfattning : This study departs in the question of what teachers really know. In cooperation with practising teachers I have investigated the knowledge that teachers develop and use in their daily work. The aim is to interpret, understand and portray this largely unformulated knowledge. LÄS MER

5. 4. Engineering Decentralized Learning in Self-Adaptive Systems

   Författare :Mirko D'Angelo; Mauro Caporuscio; Jesper Andersson; Lionel Seinturier; Linnéuniversitetet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Self-adaptive systems; Service assembly; Resiliency; Decentralized control architecture; Machine learning; Reasoning framework; Computer Science; Datavetenskap;

   Sammanfattning : Future computing environments are envisioned to be populated by myriads of pervasive real-world things, which collaborate to offer boundless opportunities to industry and society -- e.g., smart cities, and intelligent transportation systems. LÄS MER

7. 5. Reliable and Efficient Distributed Machine Learning

   Författare :Hao Chen; Ming Xiao; Mikael Skoglund; Yan Zhang; KTH; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Distributed machine learning; federated learning; communication efficiency; decentralized optimization; Electrical Engineering; Elektro- och systemteknik;

   Sammanfattning : With the ever-increasing penetration and proliferation of various smart Internet of Things (IoT) applications, machine learning (ML) is envisioned to be a key technique for big-data-driven modelling and analysis. Since massive data generated from these IoT devices are commonly collected and stored in a distributed manner, ML at the networks, e.g. LÄS MER