
Can convolutional ResNets approximately preserve input distances? A frequency analysis perspective
ResNets constrained to be biLipschitz, that is, approximately distance ...
read it

Improving Deterministic Uncertainty Estimation in Deep Learning for Classification and Regression
We propose a new model that estimates uncertainty in a single forward pa...
read it

Semisupervised Learning of Galaxy Morphology using Equivariant Transformer Variational Autoencoders
The growth in the number of galaxy images is much faster than the speed ...
read it

Capsule Networks – A Probabilistic Perspective
'Capsule' models try to explicitly represent the poses of objects, enfor...
read it

Simple and Scalable Epistemic Uncertainty Estimation Using a Single Deep Deterministic Neural Network
We propose a method for training a deterministic deep model that can fin...
read it

Try Depth Instead of Weight Correlations: Meanfield is a Less Restrictive Assumption for Deeper Networks
We challenge the longstanding assumption that the meanfield approximati...
read it

A Systematic Comparison of Bayesian Deep Learning Robustness in Diabetic Retinopathy Tasks
Evaluation of Bayesian deep learning (BDL) methods is challenging. We of...
read it

Flood Detection On Low Cost Orbital Hardware
Satellite imaging is a critical technology for monitoring and responding...
read it

Galaxy Zoo: Probabilistic Morphology through Bayesian CNNs and Active Learning
We use Bayesian convolutional neural networks and a novel generative mod...
read it

Idealised Bayesian Neural Networks Cannot Have Adversarial Examples: Theoretical and Empirical Study
We prove that idealised discriminative Bayesian neural networks, capturi...
read it

Understanding Measures of Uncertainty for Adversarial Example Detection
Measuring uncertainty is a promising technique for detecting adversarial...
read it
Lewis Smith
is this you? claim profile