Algorithmic fairness in artificial intelligence for medicine and healthcare
In healthcare, the development and deployment of insufficiently fair systems of artificial
intelligence (AI) can undermine the delivery of equitable care. Assessments of AI models …
intelligence (AI) can undermine the delivery of equitable care. Assessments of AI models …
Self-supervised learning in medicine and healthcare
The development of medical applications of machine learning has required manual
annotation of data, often by medical experts. Yet, the availability of large-scale unannotated …
annotation of data, often by medical experts. Yet, the availability of large-scale unannotated …
Doremi: Optimizing data mixtures speeds up language model pretraining
The mixture proportions of pretraining data domains (eg, Wikipedia, books, web text) greatly
affect language model (LM) performance. In this paper, we propose Domain Reweighting …
affect language model (LM) performance. In this paper, we propose Domain Reweighting …
Delving into out-of-distribution detection with vision-language representations
Recognizing out-of-distribution (OOD) samples is critical for machine learning systems
deployed in the open world. The vast majority of OOD detection methods are driven by a …
deployed in the open world. The vast majority of OOD detection methods are driven by a …
On the opportunities and risks of foundation models
AI is undergoing a paradigm shift with the rise of models (eg, BERT, DALL-E, GPT-3) that are
trained on broad data at scale and are adaptable to a wide range of downstream tasks. We …
trained on broad data at scale and are adaptable to a wide range of downstream tasks. We …
Last layer re-training is sufficient for robustness to spurious correlations
Neural network classifiers can largely rely on simple spurious features, such as
backgrounds, to make predictions. However, even in these cases, we show that they still …
backgrounds, to make predictions. However, even in these cases, we show that they still …
Towards out-of-distribution generalization: A survey
Traditional machine learning paradigms are based on the assumption that both training and
test data follow the same statistical pattern, which is mathematically referred to as …
test data follow the same statistical pattern, which is mathematically referred to as …
Disparities in dermatology AI performance on a diverse, curated clinical image set
R Daneshjou, K Vodrahalli, RA Novoa, M Jenkins… - Science …, 2022 - science.org
An estimated 3 billion people lack access to dermatological care globally. Artificial
intelligence (AI) may aid in triaging skin diseases and identifying malignancies. However …
intelligence (AI) may aid in triaging skin diseases and identifying malignancies. However …
Weak-to-strong generalization: Eliciting strong capabilities with weak supervision
Widely used alignment techniques, such as reinforcement learning from human feedback
(RLHF), rely on the ability of humans to supervise model behavior-for example, to evaluate …
(RLHF), rely on the ability of humans to supervise model behavior-for example, to evaluate …
Domain generalization: A survey
Generalization to out-of-distribution (OOD) data is a capability natural to humans yet
challenging for machines to reproduce. This is because most learning algorithms strongly …
challenging for machines to reproduce. This is because most learning algorithms strongly …