Neural networks are powerful tools for modelling complex non-linear mappings, but they often suffer from overfitting and provide no measures of uncertainty in their predictions. Bayesian techniques are proposed as a remedy to these problems, as these both regularize and provide an inherent measure of uncertainty from their posterior predictive distributions. By quantifying predictive uncertainty, we attempt to improve a systematic trading strategy by scaling positions with uncertainty. Exact Bayesian inference is often impossible, and approximate techniques must be used. For this task, this thesis compares dropout, variational inference and Markov chain Monte Carlo. We find that dropout and variational inference provide powerful regularizat...
In response to financial crises and opaque practices, governmental entities and financial regulatory...
Understanding the uncertainty of a neural network's (NN) predictions is essential for many purposes....
Recent work has shown that convolutional networks can successfully handle time series as input in va...
Neural networks are powerful tools for modelling complex non-linear mappings, but they often suffer ...
With the capability of modeling complex non-linear mappings, neural networks have obtained state-of-...
Although deep learning has made advances in a plethora of fields, ranging from financial analysis to...
Since their inception, machine learning methods have proven useful, and their usability continues to...
To metoder for å konstruere Bayesianske nevrale nettverk, MC Dropout og SGVB, er implementert og anv...
In this work, I will focus on ways in which we can build machine learning models that appropriately ...
Recent developments in Bayesian Learning have made the Bayesian view of parameter estimation applica...
An important task in brain modeling is that of estimating model parameters and quantifying their unc...
Forecasting the future is important in many applications, including forecasting future sales volumes...
Conventional training methods for neural networks involve starting al a random location in the solut...
Neural networks are an important and powerful family of models, but they have lacked practical ways ...
Kunstige nevrale nettverksmodeller har vært populære i forskjellige applikasjoner i det siste. De pr...
In response to financial crises and opaque practices, governmental entities and financial regulatory...
Understanding the uncertainty of a neural network's (NN) predictions is essential for many purposes....
Recent work has shown that convolutional networks can successfully handle time series as input in va...
Neural networks are powerful tools for modelling complex non-linear mappings, but they often suffer ...
With the capability of modeling complex non-linear mappings, neural networks have obtained state-of-...
Although deep learning has made advances in a plethora of fields, ranging from financial analysis to...
Since their inception, machine learning methods have proven useful, and their usability continues to...
To metoder for å konstruere Bayesianske nevrale nettverk, MC Dropout og SGVB, er implementert og anv...
In this work, I will focus on ways in which we can build machine learning models that appropriately ...
Recent developments in Bayesian Learning have made the Bayesian view of parameter estimation applica...
An important task in brain modeling is that of estimating model parameters and quantifying their unc...
Forecasting the future is important in many applications, including forecasting future sales volumes...
Conventional training methods for neural networks involve starting al a random location in the solut...
Neural networks are an important and powerful family of models, but they have lacked practical ways ...
Kunstige nevrale nettverksmodeller har vært populære i forskjellige applikasjoner i det siste. De pr...
In response to financial crises and opaque practices, governmental entities and financial regulatory...
Understanding the uncertainty of a neural network's (NN) predictions is essential for many purposes....
Recent work has shown that convolutional networks can successfully handle time series as input in va...