Post by Unconventional AI

Most real-world systems are dynamic.  So why do we still treat computation as static? Our latest blog by Sara Achour and Matthew Bull explores computation through motion using gyroscopes, rods, springs, and ordinary differential equations to perform handwritten digit classification. A deep dive into:  • dynamical systems as compute  • differentiable ODE solvers  • physics-inspired machine learning  • emergent computation through interaction Read here: https://lnkd.in/gWPrdmbp