What and How of Machine Learning Transparency: Building Bespoke Explainability Tools with Interoperable Algorithmic Components

Building Reliable Interoperable Distributed Objects with the Maestro Tools

This work presents the Maestro Tools for development of reliable interoperable object-oriented distributed applications. We discuss the three fundamental parts of Maestro – the object group tools, the client/object interoperability tools, and the group protocols which implement state machine replication of distributed objects – with a special focus on practical usability and system integration ...

Algorithmic Aspects of Machine Learning

Interoperable Machine Learning Metadata using MEX

One key step towards machine learning scenarios is the reproducibility of an experiment as well as the interchanging of machine learning metadata. A notorious existing problem on different machine learning architectures is either the interchangeability of measures generated by executions of an algorithm and general provenance information for the experiment configuration. This demand tends to br...

From Machine Ethics To Machine Explainability and Back

We find ourselves surrounded by a rapidly increasing number of autonomous and semi-autonomous systems. Two grand challenges arise from this development: Machine Ethics and Machine Explainability. Machine Ethics, on the one hand, is concerned with behavioral constraints for systems, set up in a formal unambiguous, algorithmizable, and implementable way, so that morally acceptable, restricted beh...

Transparency and Socially Guided Machine Learning

In this paper we advocate a paradigm of socially guided machine learning, designing agents that take better advantage of the situated aspects of learning. We augmented a standard Reinforcement Learning agent with the social mechanisms of attention direction and gaze. Experiments with an interactive computer game, deployed over the World Wide Web to over 75 players, show the positive impact of t...