Structure predictors like ESMFold fold proteins using neural network computation and have transformed structural biology. However, the driving mechanism from amino-acid (AA) sequence to 3D structure is insufficiently understood, and biological meaning remains locked in the dense network. Sparse autoencoders (SAEs) have...
Bo-Han Liu, Xiao-Han Fan, Wenqian Ye et al.· 0 citations
Deep neural networks often learn and rely on spurious correlations, i.e., superficial associations between non-causal features and the targets. For instance, an image classifier may identify camels based on the desert backgrounds. While it can yield high overall accuracy during training, it degrades generalization on m...
Wenqian Ye, Guangtao Zheng, Ai-Dong Zhang· Knowledge Discovery and Data...· 5 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.