<ul><li>A new approach has been proposed to address the problem of online distribution shift in deep learning.</li><li>The proposed method is a meta-algorithm that can enhance the performance of any online learner under non-stationarity.</li><li>It automatically adapts to changes in the data distribution and selects the most appropriate 'attention span' for learning.</li><li>Experiments show consistent improvement in classification accuracy across various real-world datasets.</li></ul>

Adapting to Online Distribution Shifts in Deep Learning: A Black-Box Approach

Discover more