Physics Enhanced Artificial Intelligence
This addresses the need for more reliable models in specific, complex applications, but it is incremental as it builds on existing portfolio theory and bias-variance concepts.
The paper tackles the problem of model trustworthiness in complex, narrow domains by proposing to combine AI/ML models with physical and expert models, proving that such combinations yield lower risk and increased user trust based on mean-variance portfolio theory and bias-variance trade-off analysis.
We propose that intelligently combining models from the domains of Artificial Intelligence or Machine Learning with Physical and Expert models will yield a more "trustworthy" model than any one model from a single domain, given a complex and narrow enough problem. Based on mean-variance portfolio theory and bias-variance trade-off analysis, we prove combining models from various domains produces a model that has lower risk, increasing user trust. We call such combined models - physics enhanced artificial intelligence (PEAI), and suggest use cases for PEAI.