MonoNet: enhancing interpretability in neural networks via monotonic features.

ABSTRACT:

Motivation

Being able to interpret and explain the predictions made by a machine learning model is of fundamental importance. Unfortunately, a trade-off between accuracy and interpretability is often observed. As a result, the interest in developing more transparent yet powerful models has grown considerably over the past few years. Interpretable models are especially needed in high-stake scenarios, such as computational biology and medical informatics, where erroneous or biased models' predictions can have deleterious consequences for a patient. Furthermore, understanding the inner workings of a model can help increase the trust in the model.

Results

We introduce a novel structurally constrained neural network, MonoNet, which is more transparent, while still retainin

SUBMITTER: Nguyen AP 

PROVIDER: S-EPMC10152389 | biostudies-literature | 2023

REPOSITORIES: biostudies-literature