Intelligence plays dice: Stochasticity is essential for machine learning
This perspective article highlights a foundational shift in understanding stochasticity's role in ML, potentially influencing future AI development.
The authors argue that stochasticity is a critical component for intelligent systems in machine learning, providing robustness, generalizability, and calibration, based on a review of ML literature and biological intelligence.
Many fields view stochasticity as a way to gain computational efficiency, while often having to trade off accuracy. In this perspective article, we argue that stochasticity plays a fundamentally different role in machine learning (ML) and is likely a critical ingredient of intelligent systems. As we review the ML literature, we notice that stochasticity features in many ML methods, affording them robustness, generalizability, and calibration. We also note that randomness seems to be prominent in biological intelligence, from the spiking patterns of individual neurons to the complex behavior of animals. We conclude with a discussion of how we believe stochasticity might shape the future of ML.