Add to ORKGWe present a new type of probabilistic model which we call DISsimilarity COefficient Networks (DISCO Nets). DISCO Nets allow us to efficiently sample from a posterior distribution parametrised by a neural network. During training, DISCO Nets are learned by minimising the dissimilarity coefficient between the true distribution and the estimated distribution. This allows us to tailor the training to the loss related to the task at hand. We empirically show that (i) by modeling uncertainty on the output value, DISCO Nets outperform equivalent non-probabilistic predictive networks and (ii) DISCO Nets accurately model the uncertainty of the output, outperforming existing probabilistic models based on deep neural networks
Any binary classifier (or score-function) can be used to define a dissimilarity between two distrib...
This paper describes a method by which a neural network learns to fit a distribution to sample data....
Estimating the uncertainty in deep neural network predictions is crucial for many real-world applica...
We present a new type of probabilistic model which we call DISsimilarity COefficient Networks (DISCO...
We investigate a novel deep-learning-based approach to estimate uncertainty in stereo disparity pred...
Recent advances in statistical inference have significantly expanded the toolbox of probabilistic mo...
Development of an accurate, flexible, and numerically efficient uncertainty quantification (UQ) meth...
Minimization of a sum-of-squares or cross-entropy error function leads to network out-puts which app...
This paper reviews the Bayesian approach to learning in neural networks, then introduces a new adapt...
The deep learning techniques have made neural networks the leading option for solving some computat...
Understanding the relationship between connectionist and probabilistic models is important for evalu...
We introduce a novel training principle for generative probabilistic models that is an al-ternative ...
Probabilistic networks, which provide compact descriptions of complex stochastic relationships among...
Deep neural networks have amply demonstrated their prowess but estimating the reliability of their p...
Neural networks are flexible models capable of capturing complicated data relationships. However, ne...
Any binary classifier (or score-function) can be used to define a dissimilarity between two distrib...
This paper describes a method by which a neural network learns to fit a distribution to sample data....
Estimating the uncertainty in deep neural network predictions is crucial for many real-world applica...
We present a new type of probabilistic model which we call DISsimilarity COefficient Networks (DISCO...
We investigate a novel deep-learning-based approach to estimate uncertainty in stereo disparity pred...
Recent advances in statistical inference have significantly expanded the toolbox of probabilistic mo...
Development of an accurate, flexible, and numerically efficient uncertainty quantification (UQ) meth...
Minimization of a sum-of-squares or cross-entropy error function leads to network out-puts which app...
This paper reviews the Bayesian approach to learning in neural networks, then introduces a new adapt...
The deep learning techniques have made neural networks the leading option for solving some computat...
Understanding the relationship between connectionist and probabilistic models is important for evalu...
We introduce a novel training principle for generative probabilistic models that is an al-ternative ...
Probabilistic networks, which provide compact descriptions of complex stochastic relationships among...
Deep neural networks have amply demonstrated their prowess but estimating the reliability of their p...
Neural networks are flexible models capable of capturing complicated data relationships. However, ne...
Any binary classifier (or score-function) can be used to define a dissimilarity between two distrib...
This paper describes a method by which a neural network learns to fit a distribution to sample data....
Estimating the uncertainty in deep neural network predictions is crucial for many real-world applica...