Research interests
I am interested in human-like reasoning and the “third wave” of artificial intelligence. Humans are capable of finding patterns in remarkably small datasets, learning from just a handful of examples. We use a wide variety of strategies to solve a wide variety of problems. Truly intelligent systems should be able to do likewise. Third-wave AI focuses on systems that can not just make predictions, but form explanations. This goes far beyond the first-wave (GOFAI, or good old fashioned AI) and second-wave (deep learning) AI. Furthermore, some speculate that third-wave AI might focus on teaching the AIs how to learn, or meta-learning.
Publications
Representational Interpretive Structure: Theory and Notation
Examining Experts’ Recommendations of Representational Systems for Problem Solving
Considerations in Representation Selection for Problem Solving: a Review
Cognitive Properties of Representations: A Framework
Automating representation change across domains for reasoning
Correspondence-based analogies for choosing problem representations
Inspection and Selection of Representations
Simulating neuromorphic reservoir computing: Abstract feed-forward hardware models
Restricted Echo State Networks
Neuromorphic Computing with Reservoir Neural Networks on Memristive Hardware
Talks
GitHub
I infrequently put projects on GitHub, but you are welcome to view what is available there: Aaron Stockdill on GitHub.