Rapid progress in machine learning for natural language processing has the potential to
transform debates about how humans learn language. However, the learning environments …

Recent work has shown that large text-based neural language models, trained with
conventional supervised learning objectives, acquire a surprising propensity for few-and …

Few-shot learning (FSL) techniques seek to learn the underlying patterns in data using
fewer samples, analogous to how humans learn from limited experience. In this limited-data …

What can neural networks learn about the visual world when provided with only a single
image as input? While any image obviously cannot contain the multitudes of all existing …

Data-driven learning uncontroversially plays a role in human language acquisition---how
large a role is a matter of much debate. The success of artificial neural networks in NLP in …

Recent advancements in machine learning (ML) and deep learning (DL) have advanced the
capabilities of analytical models, achieving unprecedented accuracy and efficiency in a wide …

High-throughput screening technologies, such as robot-controlled microscopes and whole
genome sequencing, have led to an increasing volume of unbiased biological data. An open …

Self-supervised learning has unlocked the potential of scaling up pretraining to billions of
images, since annotation is unnecessary. But are we making the best use of data? How …

Deep learning models often fail to maintain their performance on new test domains. This
problem has been regarded as a critical limitation of deep learning for realworld …