Thermodynamics-inspired Explanations of Artificial Intelligence

arXiv:2206.13475v3 Announce Type: replace-cross
Abstract: In recent years, predictive machine learning methods have gained prominence in various scientific domains. However, due to their black-box nature, it is essential to establish trust in these models before accepting them as accurate. One promising strategy for assigning trust involves employing explanation techniques that elucidate the rationale behind a black-box model's predictions in a manner that humans can understand. However, assessing the degree of human interpretability of the rationale generated by such methods is …

abstract artificial artificial intelligence arxiv box cond-mat.dis-nn cond-mat.stat-mech cs.lg domains however intelligence machine machine learning nature physics.comp-ph predictive scientific strategy them trust type