Improving interpretability of deep learning models: splicing codes as a case study
Jha, A.; Aicher, J. K.; Singh, D.; Barash, Y.
Show abstract
Despite the success and fast adaptation of deep learning models in a wide range of fields, lack of interpretability remains an issue, especially in biomedical domains. A recent promising method to address this limitation is Integrated Gradients (IG), which identifies features associated with a prediction by traversing a linear path from a baseline to a sample. We extend IG with nonlinear paths, embedding in latent space, alternative baselines, and a framework to identify important features which make it suitable for interpretation of deep models for genomics.
Matching journals
The top 3 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- Improving deep models of protein-coding potential with a Fourier-transform architecture and machine translation task 96%
- Representation Learning of Genomic Sequence Motifs with Convolutional Neural Networks 96%
- Optimal tuning of weighted kNN- and diffusion-based methods for denoising single cell genomics data 95%
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.