International audienceThe connection between Bayesian neural networks and Gaussian processes gained a lot of attention in the last few years, with the flagship result that hidden units converge to a Gaussian process limit when the layers width tends to infinity. Underpinning this result is the fact that hidden units become independent in the infinite-width limit. Our aim is to shed some light on hidden units dependence properties in practical finite-width Bayesian neural networks. In addition to theoretical results, we assess empirically the depth and width impacts on hidden units dependence properties
It is well known that artificial neural networks initialized from independent and identically distri...
The logit outputs of a feedforward neural network at initialization are conditionally Gaussian, give...
The analytic inference, e.g. predictive distribution being in closed form, may be an appealing benef...
International audienceThe connection between Bayesian neural networks and Gaussian processes gained ...
International audienceThe connection between Bayesian neural networks and Gaussian processes gained ...
We investigate deep Bayesian neural networks with Gaussian priors on the weights and ReLU-like nonli...
International audienceWe investigate deep Bayesian neural networks with Gaussian priors on the weigh...
International audienceWe investigate deep Bayesian neural networks with Gaussian priors on the weigh...
10 pages, 5 figures, ICML'19 conferenceInternational audienceWe investigate deep Bayesian neural net...
This article studies the infinite-width limit of deep feedforward neural networks whose weights are ...
Comparing Bayesian neural networks (BNNs) with different widths is challenging because, as the width...
Recent works have suggested that finite Bayesian neural networks may sometimes outperform their infi...
Les réseaux neuronaux (RN) sont des outils efficaces qui atteignent des performances de pointe dans ...
Bayesian neural networks are theoretically well-understood only in the infinite-width limit, where G...
It took until the last decade to finally see a machine match human performance on essentially any ta...
It is well known that artificial neural networks initialized from independent and identically distri...
The logit outputs of a feedforward neural network at initialization are conditionally Gaussian, give...
The analytic inference, e.g. predictive distribution being in closed form, may be an appealing benef...
International audienceThe connection between Bayesian neural networks and Gaussian processes gained ...
International audienceThe connection between Bayesian neural networks and Gaussian processes gained ...
We investigate deep Bayesian neural networks with Gaussian priors on the weights and ReLU-like nonli...
International audienceWe investigate deep Bayesian neural networks with Gaussian priors on the weigh...
International audienceWe investigate deep Bayesian neural networks with Gaussian priors on the weigh...
10 pages, 5 figures, ICML'19 conferenceInternational audienceWe investigate deep Bayesian neural net...
This article studies the infinite-width limit of deep feedforward neural networks whose weights are ...
Comparing Bayesian neural networks (BNNs) with different widths is challenging because, as the width...
Recent works have suggested that finite Bayesian neural networks may sometimes outperform their infi...
Les réseaux neuronaux (RN) sont des outils efficaces qui atteignent des performances de pointe dans ...
Bayesian neural networks are theoretically well-understood only in the infinite-width limit, where G...
It took until the last decade to finally see a machine match human performance on essentially any ta...
It is well known that artificial neural networks initialized from independent and identically distri...
The logit outputs of a feedforward neural network at initialization are conditionally Gaussian, give...
The analytic inference, e.g. predictive distribution being in closed form, may be an appealing benef...
Add to ORKG