Sökning: "Linear networks"

Visar resultat 11 - 15 av 315 uppsatser innehållade orden Linear networks.

1. 11. Digital Front End Algorithms for Sub-Band Full Duplex

   Master-uppsats, Lunds universitet/Institutionen för elektro- och informationsteknik

   Författare :Midhat Rizvi; Khaled Al-Khateeb; [2023]
   Nyckelord :Adjacent Channel Leakage Ratio; Bit Error Rate; Clipping and Filtering; Crest Factor Reduction; Digital front end; Digital Pre-Distortion Error Vector Magnitude; Frequency Division Duplex; Power Amplifier; Peak to Average Power Ratio; Peak Cancellation Crest Factor Reduction; Sub Band Full Duplex; Self-Interference Cancellation; Signal-to-Interference Noise Ratio; Signal-to-Noise Ratio; Turbo Clipping; Time Division Duplex; Technology and Engineering;

   Sammanfattning : Sub-band full duplex is a new communication scheme technology, where a single frequency band is partitioned into sub-bands for downlink (DL) and up-link(UL) transmissions, and both can take place simultaneously. The idea behind the sub-band full duplex development is to improve the throughput, and coverage and reduce the latency of the UL communication by allowing the UL reception during the DL transmission. LÄS MER

3. 12. On Linear Mode Connectivity up to Permutation of Hidden Neurons in Neural Network : When does Weight Averaging work?

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

   Författare :Adhithyan Kalaivanan; [2023]
   Nyckelord :Mode Connectivity; Representation Learning; Loss Landscape; Network Symmetry; Lägesanslutning; representationsinlärning; förlustlandskap; nätverkssymmetri;

   Sammanfattning : Neural networks trained using gradient-based optimization methods exhibit a surprising phenomenon known as mode connectivity, where two independently trained network weights are not isolated low loss minima in the parameter space. Instead, they can be connected by simple curves along which the loss remains low. LÄS MER

4. 13. Artificial Neural Networks for Financial Time Series Prediction

   Master-uppsats, Stockholms universitet/Institutionen för data- och systemvetenskap

   Författare :Dana Malas; [2023]
   Nyckelord :artificial neural networks; time series analysis; deep learning; finance; long short-term memory; simple moving average;

   Sammanfattning : Financial market forecasting is a challenging and complex task due to the sensitivity of the market to various factors such as political, economic, and social factors. However, recent advances in machine learning and computation technology have led to an increased interest in using deep learning for forecasting financial data. LÄS MER

5. 14. Channel Estimation Optimization in 5G New Radio using Convolutional Neural Networks

   Master-uppsats, Karlstads universitet/Institutionen för matematik och datavetenskap (from 2013)

   Författare :David Adolfsson; [2023]
   Nyckelord :Channel Estimation; 5G NR; CNN; Kanalestimering; 5G NR;

   Sammanfattning : Channel estimation is the process of understanding and analyzing the wireless communication channel's properties. It helps optimize data transmission by providing essential information for adjusting encoding and decoding parameters. LÄS MER

7. 15. Deep Neural Networks as SurrogateModels for Fuel Performance Codes

   Kandidat-uppsats, Uppsala universitet/Tillämpad kärnfysik

   Författare :Wenhan Zhou; [2023]
   Nyckelord :Transuranus; AI; Nuclear Fuel Rods;

   Sammanfattning : The core component of a nuclear power plant is the reactor and the fuel rods that supply it with fission fuel. Efficient and safe energy extraction is thus highly dependent on the reactor design and the conditions of the fuel rods. To anticipate high-quality operation and potential risks in advance, one must perform simulations on the fuel rods. LÄS MER