University of Washington

7 Posts

Animated graphs showing how an ensemble of fine-tuned models can provide better performance.
University of Washington

Ensemble Models Simplified: New Machine Learning Research Simplifies Ensembles

A CLIP model whose weights were the mean of an ensemble of fine-tuned models performed as well as the ensemble and better than its best-performing constituent.
Schematic of 8-bit optimizers via block-wise dynamic quantization
University of Washington

More Learning With Less Memory: Training large language models using less memory.

Researchers discovered a new way to reduce memory requirements when training large machine learning models. Tim Dettmers and colleagues at University of Washington released 8-bit optimizers that store gradient statistics as 8-bit values, while maintaining the same accuracy.
Animation showing how MERLOT is able to match contextualized captions with their corresponding video frames
University of Washington

Richer Video Representations: Pretraining Method Improves AI's Ability to Understand Video

To understand a movie scene, viewers often must remember or infer previous events and extrapolate potential consequences. New work improved a model’s ability to do the same.
System Oscar+ working
University of Washington

Sharper Eyes For Vision+Language

Models that interpret the interplay of words and images tend to be trained on richer bodies of text than images. Recent research worked toward giving such models a more balanced knowledge of the two domains.
Oren Etzioni
University of Washington

Oren Etzioni: Tools For Equality

In 2020, I hope the AI community will grapple with issues of fairness in ways that tangibly and directly benefit disadvantaged populations.
Collage with photos of people's faces
University of Washington

Public Access, Private Faces

One of the largest open datasets for training face recognition systems has its roots in a popular photo-sharing service. Companies that have used this data could find themselves liable for millions in legal recompense.
Bert and Ernie from Sesame Street
University of Washington

BERT Is Back

Less than a month after XLNet overtook BERT, the pole position in natural language understanding changed hands again. RoBERTa is an improved BERT pretraining recipe that beats its forbear, becoming the new state-of-the-art language model — for the moment.

Subscribe to The Batch

Stay updated with weekly AI News and Insights delivered to your inbox