Reliable interpretability of biology-inspired deep neural networks.

Abstract excerpt

Deep neural networks display impressive performance but suffer from limited interpretability. Biology-inspired deep learning, where the architecture of the computational graph is based on biological knowledge, enables unique interpretability where real-world concepts are encoded in hidden nodes, which can be ranked by importance and thereby interpreted. In such models trained on single-cell transcriptomes, we...

Topics

Share this publication in a Topic to start or enrich a Post.

• Share to Models, Biological
• Share to Mutation
• Share to Neural Networks, Computer