Explainable AI (XAI) investigates methods for analyzing or complementing AI models to make the internal logic and output of algorithms transparent and interpretable, making these processes humanly understandable and meaningful. Some might dispute the need for XAI, and it is true that there is no need for explainability in certain applications. This assumption may well be true in cases where the ultimate goal is the maximum performance, for example in a cat-vs-dog image classifier. This is not the case, however, when these applications concern people's lives and well-being. A system proposing a specific amount of a drug to a patient, or a system suggesting prison time for a defendant must have an element of being questionable and reasonable. Explainability of such systems will provide transparency and allow human experts to be advised, rather than blindly rely on them.
Conclusive Local Interpretation Rules for Random Forests through LionForests
A data set of 1.8 billion measurements from a mechanical wrist with three axes that can hold tools, for example, for spray painting in combination with a pump. The data set spans six months in 1-second intervals.
Using Objects and a Graph Convolutional Network for the Bottom-up Recognition and Explanation of Events in Video
An algorithm to rectify NDVI measurements from sentinel 2 images.
Our dream to make machines sense and perceive (notably see) comes true: nowadays Computer Vision enables diverse applications: - Autonomous Systems (cars, drones, vessels) Perception, - Robotics Perception and Control, - Intelligent Human-Machine Int...
Argumentative Explanations through Local Interpretations of Predictive Models
Our AI-Based Predictive Sales Software enables B2B sales managers to forecast cross-sell, churn risk accurately, and determine the appropriate pricing analytics with one click.
Interactive dialogue between user-machine learning model via explanations
A data set of 380 million measurements from a hydraulic pump that can be mounted on an industrial robot, for example, to pump liquid paint for spray painting. The data set spans two months in 1-second intervals.
A Neural-Specific Local Interpretation Technique Exploiting Penultimate Layer Information
Deep Neural Network trained for the classification of dermoscopic images into nine categories.