Essays about: "TensorFlow Probability"

Found 5 essays containing the words TensorFlow Probability.

1. 1. Evaluation of Probabilistic Programming Frameworks

   University essay from Uppsala universitet/Statistiska institutionen

   Author : Carl Munkby; [2022]
   Keywords : Computational statistics; Bayesian statistics; Probabilistic programming; Probabilistic modelling; Stan; TensorFlow Probability; Pyro; NumPyro; Markov Chain Monte Carlo; Hamiltonian Monte Carlo; NUTS;

   Abstract : In recent years significant progress has been made in the area of Probabilistic Programming, contributing to a considerably easier workflow for quantitative research in many fields. However, as new Probabilistic Programming Frameworks (PPFs) are continuously being created and developed, there is a need for finding ways of evaluating and benchmarking these frameworks. READ MORE

3. 2. Deep Bayesian Neural Networks for Prediction of Insurance Premiums

   University essay from KTH/Matematisk statistik

   Author : Nils Olsgärde; [2021]
   Keywords : Applied Mathematics; Artificial Intelligence; Artificial Neural Networks; Bayesian Neural Networks; Insurance Premiums; Vehicle Insurance; Tillämpad matematik; Artificiell intelligens; Artificiella neurala nätverk; Bayesianska neurala nätverk; försäkringspremier; fordonsförsäkringar;

   Abstract : In this project, the problem concerns predicting insurance premiums and particularly vehicle insurance premiums. These predictions were made with the help of Bayesian Neural Networks (BNNs), a type of Artificial Neural Network (ANN). The central concept of BNNs is that the parameters of the network follow distributions, which is beneficial. READ MORE

4. 3. Deep Learning for Positioning with MUSIC

   University essay from Linköpings universitet/Kommunikationssystem

   Author : Glädje Karl Olsson; [2021]
   Keywords : Positioning; Deep Learning; MUSIC; MUSIC-algorithm;

   Abstract : Estimating an object’s position can be of great interest in several applications,and there exists many different methods to do so. One approach is with Directionof Arrival (DOA) measurements from receivers to use the triangulation techniqueto estimate one or more transmitter’s position. READ MORE

5. 4. Ghosts of Our Past: Neutrino Direction Reconstruction Using Deep Neural Networks

   University essay from Uppsala universitet/Högenergifysik

   Author : Sigfrid Stjärnholm; [2021]
   Keywords : neutrino; neural network; ICECUBE; AI; convolutional neural network; CNN; askaryan emission; charged current; neutral current; CC; NC; Keras; TensoFlow; neutrino; neuralt nätverk; ICECUBE; AI; askaryan emission; Keras; TensorFlow;

   Abstract : Neutrinos are the perfect cosmic messengers when it comes to investigating the most violent and mysterious astronomical and cosmological events in the Universe. The interaction probability of neutrinos is small, and the flux of high-energy neutrinos decreases quickly with increasing energy. READ MORE

6. 5. Deep Bayesian Neural Networks for Prediction of Insurance Premiums

   University essay from KTH/Matematisk statistik

   Author : Nils Olsgärde; [2021]
   Keywords : Applied Mathematics; Artificial Intelligence; Artificial Neural Networks; Bayesian Neural Networks; Insurance Premiums; Vehicle Insurance; Tillämpad matematik; Artificiell intelligens; Artificiella neurala nätverk; Bayesianska neurala nätverk; försäkringspremier; fordonsförsäkringar;

   Abstract : In this project, the problem concerns predicting insurance premiums and particularly vehicle insurance premiums. These predictions were made with the help of Bayesian Neural Networks (BNNs), a type of Artificial Neural Network (ANN). The central concept of BNNs is that the parameters of the network follow distributions, which is beneficial. READ MORE