Engineering software 2.0 by interpolating neural networks: unifying training, solving, and calibration

arXiv:2404.10296v1 Announce Type: new
Abstract: The evolution of artificial intelligence (AI) and neural network theories has revolutionized the way software is programmed, shifting from a hard-coded series of codes to a vast neural network. However, this transition in engineering software has faced challenges such as data scarcity, multi-modality of data, low model accuracy, and slow inference. Here, we propose a new network based on interpolation theories and tensor decomposition, the interpolating neural network (INN). Instead of interpolating training data, a …

abstract artificial artificial intelligence arxiv challenges cs.ai cs.lg cs.ne data engineering evolution however intelligence network networks neural network neural networks series software the way training transition type vast