The field of meta-learning, or learning-to-learn, has seen a dramatic rise in interest in recent
years. Contrary to conventional approaches to AI where tasks are solved from scratch using …

Unrolled computation graphs arise in many scenarios, including training RNNs, tuning
hyperparameters through unrolled optimization, and training learned optimizers. Current …

Gradient-based meta-learning and hyperparameter optimization have seen significant
progress recently, enabling practical end-to-end training of neural networks together with …

Meta-learning models, or models that learn to learn, have been a long-desired target for
their ability to quickly solve new tasks. Traditional meta-learning methods can require …

Machine learning algorithms and systems are progressively becoming part of our societies,
leading to a growing need of building a vast multitude of accurate, reliable and interpretable …