Feynman Machine: The Universal Dynamical Systems Computer
This work addresses the problem of understanding brain computation for building intelligent machines, presenting a foundational model that could impact AI and neuroscience.
The authors proposed the Feynman Machine, a universal computer for dynamical systems inspired by neuroscience, to model computational processes in the brain and build intelligent machines. They demonstrated that networks of interacting dynamical systems can automatically learn sensorimotor models, identified these networks in mammalian neocortex, and applied software implementations to spatiotemporal learning tasks.
Efforts at understanding the computational processes in the brain have met with limited success, despite their importance and potential uses in building intelligent machines. We propose a simple new model which draws on recent findings in Neuroscience and the Applied Mathematics of interacting Dynamical Systems. The Feynman Machine is a Universal Computer for Dynamical Systems, analogous to the Turing Machine for symbolic computing, but with several important differences. We demonstrate that networks and hierarchies of simple interacting Dynamical Systems, each adaptively learning to forecast its evolution, are capable of automatically building sensorimotor models of the external and internal world. We identify such networks in mammalian neocortex, and show how existing theories of cortical computation combine with our model to explain the power and flexibility of mammalian intelligence. These findings lead directly to new architectures for machine intelligence. A suite of software implementations has been built based on these principles, and applied to a number of spatiotemporal learning tasks.