Jacobian-Enhanced Neural Networks

arXiv:2406.09132v1 Announce Type: new
Abstract: Jacobian-Enhanced Neural Networks (JENN) are densely connected multi-layer perceptrons, whose training process is modified to predict partial derivatives accurately. Their main benefit is better accuracy with fewer training points compared to standard neural networks. These attributes are particularly desirable in the field of computer-aided design, where there is often the need to replace computationally expensive, physics-based models with fast running approximations, known as surrogate models or meta-models. Since a surrogate emulates the original model accurately …

abstract accuracy arxiv attributes benefit computer cs.lg derivatives design layer networks neural networks process standard training type