Essays about: "Tidsserieprognostisering"

Found 3 essays containing the word Tidsserieprognostisering.

1. 1. Comparing decentralized learning to Federated Learning when training Deep Neural Networks under churn

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

   Author : Johan Vikström; [2021]
   Keywords : Peer- to- Peer; Decentralized Machine Learning; Federated Learning; Gossip Learning; Long Short- Term Memory; Convolutional Neural Network; Peer- to- peer; Decentraliserad Maskininlärning; Federated learning; Gossip learning; Lång korttidsminne;

   Abstract : Decentralized Machine Learning could address some problematic facets with Federated Learning. There is no central server acting as an arbiter of whom or what may benefit from Machine Learning models created by the vast amount of data becoming available in recent years. READ MORE

3. 2. Federated Learning in Large Scale Networks : Exploring Hierarchical Federated Learning

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

   Author : Henrik Eriksson; [2020]
   Keywords : Federated learning; personalization; time series forecasting; clustering; hierarchical federated learning; model interpolation; Mapper; HierFAvg; base stations; non-IID; LSTM; Federerad inlärning; tidsserieprognostisering; personalisering; kluster; hierarkisk federerad inlärning; modellinterpolation; Mapper; HierFAvg; basstationer;

   Abstract : Federated learning faces a challenge when dealing with highly heterogeneous data and it can sometimes be inadequate to adopt an approach where a single model is trained for usage at all nodes in the network. Different approaches have been investigated to succumb this issue such as adapting the trained model to each node and clustering the nodes in the network and train a different model for each cluster where the data is less heterogeneous. READ MORE

4. 3. Federated Learning for Time Series Forecasting Using Hybrid Model

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

   Author : Yuntao Li; [2019]
   Keywords : Federated Learning; Time Series Forecasting; Recurrent Neural Networks; Long Short-Term Memory; Hybrid Model; Federerad Inlärning; Tidsserieprognostisering; Återkommande Neurala Nätverk; LSTMs; Hybrida Modeller;

   Abstract : Time Series data has become ubiquitous thanks to affordable edge devices and sensors. Much of this data is valuable for decision making. In order to use these data for the forecasting task, the conventional centralized approach has shown deficiencies regarding large data communication and data privacy issues. READ MORE