Alexandra Brintrup

Uncertainty in Neural Networks: Bayesian Ensembling.

2018 · arXiv (Cornell University)

Understanding the uncertainty of a neural network's (NN) predictions is essential for many applications. The Bayesian framework provides a principled approach to this, however applying it to NNs is challenging due to the large number …

Data Considerations in Graph Representation Learning for Supply Chain Networks

2021 · arXiv (Cornell University)

Supply chain network data is a valuable asset for businesses wishing to understand their ethical profile, security of supply, and efficiency. Possession of a dataset alone however is not a sufficient enabler of actionable decisions …

Coalitional Bayesian Autoencoders -- Towards explainable unsupervised deep learning

2021 · arXiv (Cornell University)

This paper aims to improve the explainability of Autoencoder's (AE) predictions by proposing two explanation methods based on the mean and epistemic uncertainty of log-likelihood estimate, which naturally arise from the probabilistic formulation of the …

Do Autoencoders Need a Bottleneck for Anomaly Detection?

2022 · arXiv (Cornell University)

A common belief in designing deep autoencoders (AEs), a type of unsupervised neural network, is that a bottleneck is required to prevent learning the identity function. Learning the identity function renders the AEs useless for …