<ul><li>Data-driven techniques have emerged as a promising alternative to traditional numerical methods for solving PDEs.</li><li>In this work, the benefits of using memory for modeling time-dependent PDEs are investigated.</li><li>The Memory Neural Operator (MemNO) architecture effectively models memory in PDEs.</li><li>Empirical demonstrations show that MemNO outperforms baselines without memory, with up to 6x reduction in test error.</li></ul>

On the Benefits of Memory for Modeling Time-Dependent PDEs

Discover more