Artificial Intelligence Must Be Made More Scientific
Peter V. Coveney, Roger Highfield
Abstract
The role of AI within science is growing. Here we assess its impact on research and argue that AI often lacks reproducibility, transparency, objectivity, and mechanistic understanding. To ensure AI benefits research, we need to develop forms of AI that are fully compatible with the scientific method.
Topics & Concepts
Computer scienceArtificial intelligenceData scienceCognitive sciencePsychologyComputational Physics and Python ApplicationsFractal and DNA sequence analysisComputability, Logic, AI Algorithms