All sources cited or reviewed
This is a list of all sources we have used in the TransferLab, with links to the referencing content and metadata, like accompanying code, videos, etc. If you think we should look at something, drop us a line
References
[Dax21B]
Bayesian Deep Learning via Subnetwork Inference,
[Esc21M]
Mixtures of Laplace Approximations for Improved Post-Hoc Uncertainty in Deep Learning,
[Gha15P]
Probabilistic machine learning and artificial intelligence,
[Imm21I]
Improving predictions of Bayesian neural nets via local linearization,
[Izm21W]
What Are Bayesian Neural Network Posteriors Really Like?,
[Kri20B]
Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks,
[Kun19L]
Limitations of the empirical Fisher approximation for natural gradient descent,
[Osa19P]
Practical Deep Learning with Bayesian Principles,
[Pha22C]
Composable Effects for Flexible and Accelerated Probabilistic Programming in NumPyro,
[Qiu20Q]
Quantifying Point-Prediction Uncertainty in Neural Networks via Residual Estimation with an I/O Kernel,
[Ras06G]
Gaussian processes for machine learning,
[Rit18S]
A Scalable Laplace Approximation for Neural Networks,
[Wil20B]
Bayesian deep learning and a probabilistic perspective of generalization,
[You22B]
Bayesian Modeling and Uncertainty Quantification for Learning to Optimize: What, Why, and How,
[Al-18S]
Solving Nonlinear and High-Dimensional Partial Differential Equations via Deep Learning,
[Bar19L]
Learning data-driven discretizations for partial differential equations,
[Ber18U]
A unified deep artificial neural network approach to partial differential equations in complex geometries,
[Che07S]
Second-order backward stochastic differential equations and fully nonlinear parabolic PDEs,
[Dis94N]
Neural-network-based approximations for solving partial differential equations,
[E17D]
Deep Learning-Based Numerical Methods for High-Dimensional Parabolic Partial Differential Equations and Backward Stochastic Differential Equations,
[E18D]
The Deep Ritz method: A deep learning-based numerical algorithm for solving variational problems,
[Fuk20L]
Limitations of physics informed machine learning for nonlinear two-phase transport inn porous media,
[Gro18P]
A proof that artificial neural networks overcome the curse of dimensionality in the numerical approximation of Black-Scholes partial differential equations,
[Han18S]
Solving high-dimensional partial differential equations using deep learning,
[Kha19V]
Variational Physics-Informed Neural Networks For Solving Partial Differential Equations,
[Lad15D]
Data-driven fluid simulations using regression forests,