Causality in Neural Networks -- An Extended Abstract

TL;DR

This paper discusses integrating causality into neural networks to enhance explainability, fairness, and transfer learning, emphasizing the importance of causal reasoning for trustworthy AI systems.

Contribution

It introduces the application of causal reasoning concepts to deep learning models to improve their interpretability and fairness, highlighting the benefits of causal disentanglement.

Findings

Causality improves model explainability

Causal disentanglement aids transfer learning

Causality enhances fairness in AI models

Abstract

Causal reasoning is the main learning and explanation tool used by humans. AI systems should possess causal reasoning capabilities to be deployed in the real world with trust and reliability. Introducing the ideas of causality to machine learning helps in providing better learning and explainable models. Explainability, causal disentanglement are some important aspects of any machine learning model. Causal explanations are required to believe in a model's decision and causal disentanglement learning is important for transfer learning applications. We exploit the ideas of causality to be used in deep learning models to achieve better and causally explainable models that are useful in fairness, disentangled representation, etc.