GitHub - deepmind/dm_nevis: NEVIS'22: Benchmarking the next generation of never-ending learners

NEVIS'22 is a benchmark for measuring the performance of algorithms in the field of continual learning. Please see the accompanying paper for more details. NEVIS'22 is composed of 106 tasks chronologically sorted and extracted from publications randomly sampled from online proceedings of major computer vision conferences over the past three decades. Each task is a supervised classification task, which is the most well understood setting in machine learning. The challenge is how to automatically transfer knowledge across related tasks in order to achieve a higher performance or be more efficient on the next task.