Search Results for author:
Found 10 papers, 8 papers with code
Learning Predictive and Interpretable Timeseries Summaries from ICU Data
Machine learning models that utilize patient data across time (rather than just the most recent measurements) have increased performance for many risk stratification tasks in the intensive care unit.
Benchmarks, Algorithms, and Metrics for Hierarchical Disentanglement
In representation learning, there has been recent interest in developing algorithms to disentangle the ground-truth generative factors behind a dataset, and metrics to quantify how fully this occurs.
Evaluating the Interpretability of Generative Models by Interactive Reconstruction
On synthetic datasets, we find performance on this task much more reliably differentiates entangled and disentangled models than baseline approaches.
Ensembles of Locally Independent Prediction Models
Ensembles depend on diversity for improved performance.
Tackling Climate Change with Machine Learning
Climate change is one of the greatest challenges facing humanity, and we, as machine learning experts, may wonder how we can help.
Training Machine Learning Models by Regularizing their Explanations
In this thesis, we explore the possibility of training machine learning models (with a particular focus on neural networks) using explanations themselves.
Learning Qualitatively Diverse and Interpretable Rules for Classification
There has been growing interest in developing accurate models that can also be explained to humans.
Human-in-the-Loop Interpretability Prior
We often desire our models to be interpretable as well as accurate.
Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients
Deep neural networks have proven remarkably effective at solving many classification problems, but have been criticized recently for two major weaknesses: the reasons behind their predictions are uninterpretable, and the predictions themselves can often be fooled by small adversarial perturbations.
Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations
Neural networks are among the most accurate supervised learning methods in use today, but their opacity makes them difficult to trust in critical applications, especially when conditions in training differ from those in test.
