UPDATE: The workshop proceedings are available as a Zenodo Community at:
https://zenodo.org/communities/hmieai2022/
Early-bird tickets to the main conference is available up until the 16th of May
You are cordially invited to participate in the first international workshop on Heterodox Methods for Interpretable and Efficient AI, which is to be colocated with the first international conference on Hybrid Human-AI (HHAI) in Amsterdam on June 13th 2022.
In this workshop we will discuss (machine learning) architectures where the human involvement in the design 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 is much less defined a priori. The goal is 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 more efficiently.
In particular, the workshop will features invited talks and presentations on topics such as
- Transparent, Explainable and Interpretable AI/machine learning
- Bayesian networks
- Genetic programming and design
- Probabilistic deterministic finite automata
- Human-in-the-loop/Human-machine interaction
- Gamification and games AI
- Explainable evolutionary computation
- Grammatical inference
- Tsetlin machines
- Symbolic regression
- Robustness and stability of statistical models
- Applications of explainable AI
Contact e-mail: pettter+hmieai[at]cs.umu.se