Diego Febbe

Spectral Higher-Order Neural Networks can drastically reduce computational costs while improving performance on notoriously difficult tasks like N-bit parity.

Planted attractors in Neural-ODEs can transform classification tasks by directing inputs to their target classes through dynamically shaped velocity fields.

Higher-order neural networks don't need hypergraphs: SHONNs unlock their power for general-purpose feedforward architectures by sidestepping stability and scaling issues.