Log In Sign Up

Entropy-based Logic Explanations of Neural Networks

by   Pietro Barbiero, et al.

Explainable artificial intelligence has rapidly emerged since lawmakers have started requiring interpretable models for safety-critical domains. Concept-based neural networks have arisen as explainable-by-design methods as they leverage human-understandable symbols (i.e. concepts) to predict class memberships. However, most of these approaches focus on the identification of the most relevant concepts but do not provide concise, formal explanations of how such concepts are leveraged by the classifier to make predictions. In this paper, we propose a novel end-to-end differentiable approach enabling the extraction of logic explanations from neural networks using the formalism of First-Order Logic. The method relies on an entropy-based criterion which automatically identifies the most relevant concepts. We consider four different case studies to demonstrate that: (i) this entropy-based criterion enables the distillation of concise logic explanations in safety-critical domains from clinical data to computer vision; (ii) the proposed approach outperforms state-of-the-art white-box models in terms of classification accuracy.


Provable concept learning for interpretable predictions using variational inference

In safety critical applications, practitioners are reluctant to trust ne...

Enabling Verification of Deep Neural Networks in Perception Tasks Using Fuzzy Logic and Concept Embeddings

One major drawback of deep convolutional neural networks (CNNs) for use ...

Logic Explained Networks

The large and still increasing popularity of deep learning clashes with ...

Encoding Concepts in Graph Neural Networks

The opaque reasoning of Graph Neural Networks induces a lack of human tr...

Process Knowledge-infused Learning for Suicidality Assessment on Social Media

Improving the performance and natural language explanations of deep lear...

ECLAD: Extracting Concepts with Local Aggregated Descriptors

Convolutional neural networks are being increasingly used in critical sy...