The workshop Heterodox Methods for Interpretable and Efficient Artificial Intelligence (HMIEAI 2022) took place at Vrije Universiteit Amsterdam on June 13, 2022. It was organised as part of the First International Conference on Hybrid Human-Artificial Intelligence (HHAI 2022). The workshop was attended by up to 41 participants.

At HMIEAI we discussed architectures where the human involvement in the design and creation of the model and its data ingestion process allows for both more energy efficient and more interpretable outcomes. Examples of such systems stretch from pure grammatical inference methods and probabilistic programming, where the model (family) is entirely constructed by human hands and only very specific model parameters are learned from data to various types of interpretable neural network approaches where the specific workings of the output system are much less defined a priori. The goal was to spread knowledge about lesser-known approaches to learning from data that use an increased level of human involvement, require less training data, and are tailored to achieve interpretable results in a more efficient way.

The papers presented at this workshop are published as Open Access proceedings on Zenodo.

The workshop was organized by the following people, who also are editors of these proceedings: 

• Silja Renooij, Utrecht University
• Petter Ericson, Umeå University
• Victor de Boer, Vrije Universiteit Amsterdam
• Anna Jonsson, Umeå University
• Adam Dahlgren Lindström, Umeå University
• Andrew Lensen, Te Herenga Waka—Victoria University of Wellington       
• Ronald Siebes, Vrije Universiteit Amsterdam