The development of "intelligent" systems that can take decisions and perform autonomously might lead to faster and more consistent decisions. A limiting factor for a broader adoption of AI technology is the inherent risks that come with giving up human control and oversight to "intelligent" machines. Forsensitive tasks involving critical infrastructures and affecting human well-being or health, it is crucial to limit the possibility of improper, non-robust and unsafe decisions and actions. Before deploying an AI system, we see a strong need to validate its behavior, and thus establish guarantees that it will continue to perform as expected when deployed in a real-world environment. In pursuit of that objective, ways for humans to verify the agreement between the AI decision structure and their own ground-truth knowledge have been explored. Explainable AI (XAI) has developed as a subfield of AI, focused on exposing complex AI models to humans in a systematic and interpretable manner.

Towards Explainable Artificial Intelligence.- Transparency: Motivations and Challenges.- Interpretability in Intelligent Systems: A New Concept?.- Understanding Neural Networks via Feature Visualization: A Survey.- Interpretable Text-to-Image Synthesis with Hierarchical Semantic Layout Generation.- Unsupervised Discrete Representation Learning.- Towards Reverse-Engineering Black-Box Neural Networks.- Explanations for Attributing Deep Neural Network Predictions.- Gradient-Based Attribution Methods.- Layer-Wise Relevance Propagation: An Overview.- Explaining and Interpreting LSTMs.- Comparing the Interpretability of Deep Networks via Network Dissection.- Gradient-Based vs. Propagation-Based Explanations: An Axiomatic Comparison.- The (Un)reliability of Saliency Methods.- Visual Scene Understanding for Autonomous Driving Using Semantic Segmentation.- Understanding Patch-Based Learningof Video Data by Explaining Predictions.- Quantum-Chemical Insights from Interpretable Atomistic Neural Networks.- Interpretable Deep Learning in Drug Discovery.- Neural Hydrology: Interpreting LSTMs in Hydrology.- Feature Fallacy: Complications with Interpreting Linear Decoding Weights in fMRI.- Current Advances in Neural Decoding.- Software and Application Patterns for Explanation Methods.