Sökning: "Bayesian network"

Visar resultat 21 - 25 av 137 uppsatser innehållade orden Bayesian network.

1. 21. Exploring Column Update Elimination Optimization for Spike-Timing-Dependent Plasticity Learning Rule

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

   Författare :Ojasvi Singh; [2022]
   Nyckelord :Spike-Timing Dependent Plasticity; neuromorphic computing; Hebbian Learning; Spiking Neural Networks; memory optimization.; Spike-Timing Beroende Plasticitet; neuromorfisk beräkning; Hebbiansk inlärning; Spiking Neural Networks; Minnes optimering;

   Sammanfattning : Hebbian learning based neural network learning rules when implemented on hardware, store their synaptic weights in the form of a two-dimensional matrix. The storage of synaptic weights demands large memory bandwidth and storage. LÄS MER

3. 22. Path Choice Estimation in Urban Rails : Asimulation based optimisation for frequency-based assignment model

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

   Författare :Alexander Adolfsson; [2022]
   Nyckelord :Black-Box Optimisation; Optimization; Simulation based optimisation; Transit Network; Automaton; Urban Transport; Public transportation; Black-Box optimering; Optimering; Simuleringsbaserad Optimering; Transportsystem; Automation; Local Transport; Kollektivtrafik;

   Sammanfattning : Transit system have a large importance in modern urban cities, with urban rail often acting as the central system with it efficient travel time and great capacity. As cities grow in population, so to does the usage of urban rail resulting in increased crowding on the platform and in the trains. LÄS MER

4. 23. Uncertainty quantification for neural network predictions

   Magister-uppsats, Umeå universitet/Statistik

   Författare :Jonas Borgström; [2022]
   Nyckelord :;

   Sammanfattning : Since their inception, machine learning methods have proven useful, and their usability continues to grow as new methods are introduced. However, as these methods are used for decision-making in most fields, such as weather forecasting,medicine, and stock market prediction, their reliability must be appropriately evaluated before the models are deployed. LÄS MER

5. 24. Assessing Machine Learning Algorithms to Develop Station-based Forecasting Models for Public Transport : Case Study of Bus Network in Stockholm

   Master-uppsats, KTH/Transportplanering

   Författare :Mahsa Movaghar; [2022]
   Nyckelord :Public transport; ridership; machine learning; Multiple Linear Regression; Decision Tree; Random Forest; Bayesian Ridge Regression; Neural Networks; Support Vector Machines; K-Nearest Neighbors;

   Sammanfattning : Public transport is essential for both residents and city planners because of its environmentally and economically beneficial characteristics. During the past decade climatechange, coupled with fuel and energy crises have attracted significant attention toward public transportation. LÄS MER

7. 25. Role of Context in Episodic Memory : A Bayesian-Hebbian Neural Network Model of Episodic Recall

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

   Författare :Rohan Raj; [2022]
   Nyckelord :episodic memory; long-term memory; Bayesian Confidence Propagation Neural Network; synaptic plasticity; plasticity modulation; computational neuroscience;

   Sammanfattning : Episodic memory forms a fundamental aspect of human memory that accounts for the storage of events as well as the spatio-temporal relations between events during a lifetime. These spatio-temporal relations in which episodes are embedded can be understood as their contexts. Contexts play a crucial role in episodic memory retrieval. LÄS MER