The paper (arXiv 2020, also AI review 2023) opens up with discussing recent high-profile AI debates: the Montréal AI Debate and the AAAI 2020 fireside chat with Kahneman, Hinton, LeCun, and Bengio. A consensus seems to be emerging: for AI to be robust and trustworthy, it must combine learning with reasoning. Kahneman’s “System 1 vs. System 2” dual framing of cognition maps well to deep learning and symbolic reasoning. And AI needs both.

Paper (and post) introduced to me the idea of the logic tensor network, which genuinely looks quite different interesting. I hope to see adoption of the architecture in the future.

The paper (2023) argues for integrating two historically divergent traditions in artificial intelligence (neural networks and symbolic reasoning) into a unified paradigm called Neurosymbolic AI. It argues that the path to capable, explainable, and trustworthy artificial intelligence lies in marrying perception-driven neural systems with structure-aware symbolic models.

This is a description of the Scmutils system, an integrated library of procedures, embedded in the programming language Scheme, and intended to support teaching and research in mathematical physics and electrical engineering. Scmutils and Scheme are particularly effective in work where the almost-functional nature of Scheme is advantageous, such as classical mechanics, where many of the procedures are most easily formulated as quite abstract manipulations of functions.