Intelligent Matrix Exponentiation
From MaRDI portal
Abstract: We present a novel machine learning architecture that uses the exponential of a single input-dependent matrix as its only nonlinearity. The mathematical simplicity of this architecture allows a detailed analysis of its behaviour, providing robustness guarantees via Lipschitz bounds. Despite its simplicity, a single matrix exponential layer already provides universal approximation properties and can learn fundamental functions of the input, such as periodic functions or multivariate polynomials. This architecture outperforms other general-purpose architectures on benchmark problems, including CIFAR-10, using substantially fewer parameters.
This page was built for publication: Intelligent Matrix Exponentiation
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6346780)
