Search Results for author:
Found 20 papers, 6 papers with code
Adversarial Nibbler: A Data-Centric Challenge for Improving the Safety of Text-to-Image Models
To address this need, we introduce the Adversarial Nibbler challenge.
Plex: Towards Reliability using Pretrained Large Model Extensions
A recent trend in artificial intelligence is the use of pretrained models for language and vision tasks, which have achieved extraordinary performance but also puzzling failures.
Uncertainty Baselines: Benchmarks for Uncertainty & Robustness in Deep Learning
In this paper we introduce Uncertainty Baselines: high-quality implementations of standard and state-of-the-art deep learning methods on a variety of tasks.
Large-scale machine learning-based phenotyping significantly improves genomic discovery for optic nerve head morphology
A GWAS of ML-based VCDR identified 299 independent genome-wide significant (GWS; $P\leq5\times10^{-8}$) hits in 156 loci.
Underspecification Presents Challenges for Credibility in Modern Machine Learning
Predictors returned by underspecified pipelines are often treated as equivalent based on their training domain performance, but we show here that such predictors can behave very differently in deployment domains.
Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift
Using this one line code change, we achieve state-of-the-art on recent covariate shift benchmarks and an mCE of 60. 28\% on the challenging ImageNet-C dataset; to our knowledge, this is the best result for any model that does not incorporate additional data augmentation or modification of the training pipeline.
Population-Based Black-Box Optimization for Biological Sequence Design
The cost and latency of wet-lab experiments requires methods that find good sequences in few experimental rounds of large batches of sequences--a setting that off-the-shelf black-box optimization methods are ill-equipped to handle.
Fair treatment allocations in social networks
Simulations of infectious disease spread have long been used to understand how epidemics evolve and how to effectively treat them.
Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift
Modern machine learning methods including deep learning have achieved great success in predictive accuracy for supervised learning tasks, but may still fall short in giving useful estimates of their predictive {\em uncertainty}.
TensorFlow.js: Machine Learning for the Web and Beyond
TensorFlow. js is a library for building and executing machine learning algorithms in JavaScript.
Avoiding a Tragedy of the Commons in the Peer Review Process
In this position paper, we argue that a tragedy of the commons outcome may be avoided by emphasizing the professional aspects of this service.
BriarPatches: Pixel-Space Interventions for Inducing Demographic Parity
We introduce the BriarPatch, a pixel-space intervention that obscures sensitive attributes from representations encoded in pre-trained classifiers.
Rapid Prediction of Electron-Ionization Mass Spectrometry using Neural Networks
When confronted with a substance of unknown identity, researchers often perform mass spectrometry on the sample and compare the observed spectrum to a library of previously-collected spectra to identify the molecule.
AutoGraph: Imperative-style Coding with Graph-based Performance
In machine learning, imperative style libraries like Autograd and PyTorch are easy to write, but suffer from high interpretive overhead and are not easily deployable in production or mobile settings.
No Classification without Representation: Assessing Geodiversity Issues in Open Data Sets for the Developing World
Further, we analyze classifiers trained on these data sets to assess the impact of these training distributions and find strong differences in the relative performance on images from different locales.
Direct-Manipulation Visualization of Deep Networks
The recent successes of deep learning have led to a wave of interest from non-experts.
TensorFlow Estimators: Managing Simplicity vs. Flexibility in High-Level Machine Learning Frameworks
Our focus is on simplifying cutting edge machine learning for practitioners in order to bring such technologies into production.
Google Vizier: A Service for Black-Box Optimization
Any sufficiently complex system acts as a black box when it becomes easier to experiment with than to understand.
AutoMOS: Learning a non-intrusive assessor of naturalness-of-speech
Developers of text-to-speech synthesizers (TTS) often make use of human raters to assess the quality of synthesized speech.
Hidden Technical Debt in Machine Learning Systems
Machine learning offers a fantastically powerful toolkit for building useful complexprediction systems quickly.
