-
Can Your AI Differentiate Cats from Covid-19? Sample Efficient Uncertainty Estimation for Deep Learning Safety
Deep Neural Networks (DNNs) are known to make highly overconfident predi...
read it
-
Interpreting Uncertainty in Model Predictions For COVID-19 Diagnosis
COVID-19, due to its accelerated spread has brought in the need to use a...
read it
-
Multi-Loss Sub-Ensembles for Accurate Classification with Uncertainty Estimation
Deep neural networks (DNNs) have made a revolution in numerous fields du...
read it
-
Maximizing Overall Diversity for Improved Uncertainty Estimates in Deep Ensembles
The inaccuracy of neural network models on inputs that do not stem from ...
read it
-
Dropout Strikes Back: Improved Uncertainty Estimation via Diversity Sampled Implicit Ensembles
Modern machine learning models usually do not extrapolate well, i.e., th...
read it
-
Deep Confidence: A Computationally Efficient Framework for Calculating Reliable Errors for Deep Neural Networks
Deep learning architectures have proved versatile in a number of drug di...
read it
-
Sample Efficient Learning of Image-Based Diagnostic Classifiers Using Probabilistic Labels
Deep learning approaches often require huge datasets to achieve good gen...
read it
Sample Efficient Uncertainty Estimation for Deep Learning Safety
Deep Neural Networks (DNNs) are known to make highly overconfident predictions on Out-of- Distribution data. Recent research has shown that uncertainty-aware models, such as, Bayesian Neural Network (BNNs) and Deep Ensembles, are less susceptible to this issue. However research in this area has been largely confined to the big data setting. In this work, we show that even state-of-the-art BNNs and Ensemble models tend to make overconfident predictions when the amount of training data is insufficient. This is especially concerning for emerging applications in physical sciences and healthcare where overconfident and inaccurate predictions can lead to disastrous consequences. To address the issue of accurate uncertainty (or confidence) estimation in the small-data regime, we propose a probabilistic generalization of the popular sample-efficient non-parametric kNN approach. We demonstrate the usefulness of the proposed approach on a real-world application of COVID-19 diagnosis from chest X-Rays.
READ FULL TEXT
Comments
There are no comments yet.