Sökning: "Weights"
Visar resultat 1 - 5 av 702 uppsatser innehållade ordet Weights.
1. Optical Communication using Nanowires and Molecular Memory Systems
Master-uppsats, Lunds universitet/Fysiska institutionen; Lunds universitet/SynkrotronljusfysikSammanfattning : Neuromorphic computational networks, inspired by biological neural networks, provide a possible way of lowering computational energy cost, while at the same time allowing for much more sophisticated devices capable of real-time inferences and learning. Since simulating artificial neural networks on conventional computers is particularly inefficient, the development of neuromorphic devices is strongly motivated as the reliance on AI-models increases. LÄS MER
2. Multicriteria Evaluation in Real Estate Land-use Suitability Analysis: The case of Volos, Greece
Master-uppsats, Lunds universitet/Institutionen för naturgeografi och ekosystemvetenskapSammanfattning : The integration of Geographic Information Systems (GIS) into real estate analysis has long been considered an interesting interdisciplinary pursuit, but has yet to become mainstream. Despite the increasing academic focus over the last twenty years, this endeavour has mostly been approached from the scientific side of Geography. LÄS MER
3. Integrating Local Knowledge into the Spatial Analysis of Wind Power: The case study of Northern Tzoumerka, Greece
Master-uppsats, Lunds universitet/Institutionen för naturgeografi och ekosystemvetenskapSammanfattning : Increasing demand for incorporating renewable energy projects into the national energy mix, is associated with international and European efforts to tackle the negative effects of climate change and strengthen energy resilience. Greece, as a member country of the European Union, has acknowledged that necessity, by implementing a national program aiming to significantly reduce Green House Gas Emissions and upscale Renewable Energy Sources (RES) project development in upcoming years. LÄS MER
4. Attack Strategies in Federated Learning for Regression Models : A Comparative Analysis with Classification Models
Master-uppsats, Umeå universitet/Institutionen för datavetenskapSammanfattning : Federated Learning (FL) has emerged as a promising approach for decentralized model training across multiple devices, while still preserving data privacy. Previous research has predominantly concentrated on classification tasks in FL settings, leaving a noticeable gap in FL research specifically for regression models. LÄS MER
5. Attack Strategies in Federated Learning for Regression Models : A Comparative Analysis with Classification Models
Master-uppsats, Umeå universitet/Institutionen för tillämpad fysik och elektronikSammanfattning : Federated Learning (FL) has emerged as a promising approach for decentralized model training across multiple devices, while still preserving data privacy. Previous research has predominantly concentrated on classification tasks in FL settings, leaving a noticeable gap in FL research specifically for regression models. LÄS MER