Essays about: "Bayesian Neural Network"

Showing result 11 - 15 of 69 essays containing the words Bayesian Neural Network.

1. 11. Non-Bayesian Out-of-Distribution Detection Applied to CNN Architectures for Human Activity Recognition

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

   Author : Serghei Socolovschi; [2022]
   Keywords : Human Activity Recognition; Deep Learning; Time Series; Uncertainty Estimation; Outofdistribution Detection; Convolutional Neural Network; Human Activity Recognition; Deep Learning; Tidsserie; Uppskattning av Osäkerheten; Outofdistribution Detection; Convolutional Neural Network;

   Abstract : Human Activity Recognition (HAR) field studies the application of artificial intelligence methods for the identification of activities performed by people. Many applications of HAR in healthcare and sports require the safety-critical performance of the predictive models. READ MORE

3. 12. Evolutionary Properties of Neural Networks: Exploration of Robustness and Evolvability in the Genotype-Phenotype Map

   University essay from Lunds universitet/Beräkningsbiologi och biologisk fysik - Genomgår omorganisation

   Author : Daesung Cho; [2022]
   Keywords : robustness; evolvability; genotype-phenotype map; canalization; Bayesian inference; simulation-based inference; information theory; neural networks; pyloric rhythm; Physics and Astronomy;

   Abstract : Evolution is a fundamental and crucial part of life that hinges on two central properties: robustness and evolvability. Robustness is required to maintain essential traits despite mutations while evolvability produces novel traits that might prove beneficial in survival. READ MORE

4. 13. Towards Deep Learning Accelerated Sparse Bayesian Frequency Estimation

   University essay from Lunds universitet/Matematisk statistik

   Author : Mika Persson; [2022]
   Keywords : Bayesian Statistics; Deep Learning; Frequency Estimation; Generative Adversarial Networks; Artificial Neural Networks; Statistical Modelling; Mathematics and Statistics;

   Abstract : The Discrete Fourier Transform is the simplest way to obtain the spectrum of a discrete complex signal. This thesis concerns the case when the signal is known to contain a small (unknown) number of frequencies, not limited to the discrete Fourier frequencies, embedded in complex Gaussian noise. READ MORE

5. 14. Prediction of appropriate L2 regularization strengths through Bayesian formalism

   University essay from Lunds universitet/Beräkningsbiologi och biologisk fysik - Genomgår omorganisation; Lunds universitet/Institutionen för astronomi och teoretisk fysik - Genomgår omorganisation

   Author : Alexander Degener; [2022]
   Keywords : Machine learning; Artificial Neural Network; L2 regularization strength; Bayesian formalism; Classification tasks; Physics and Astronomy;

   Abstract : This paper proposes and investigates a Bayesian relation between optimal L2 regularization strengths and the number of training patterns and hidden nodes used for an artificial neural network. The results support the proposed dependence for number of training patterns, while the dependence on hidden architecture was less clear. READ MORE

6. 15. Inverse Uncertainty Quantification for Sounding Rocket Dispersion

   University essay from KTH/Matematik (Avd.)

   Author : Tove Ågren; [2022]
   Keywords : Uncertainty quantification; Bayesian inference; Rocket dispersion; Neural networks; Markov Chain Monte Carlo.; Osäkerhetskvantifiering; Bayesiansk inferens; Raketspridning; Neurala nätverk; Markovkedje-Monte Carlo;

   Abstract : Sounding rocket impact points are subject to dispersion due to uncertainties in simulation model parameters and perturbations of the rocket trajectory during flight. Estimating the area of dispersion assumes that associated model uncertainties and magnitude of perturbations have already been inferred. READ MORE