Summary of Interpolating Neural Network: a Novel Unification Of Machine Learning and Interpolation Theory, by Chanwook Park et al.
Interpolating neural network: A novel unification of machine learning and interpolation theory
by Chanwook Park, Sourav Saha, Jiachen Guo, Hantao Zhang, Xiaoyu Xie, Miguel A. Bessa, Dong Qian, Wei Chen, Gregory J. Wagner, Jian Cao, Wing Kam Liu
First submitted to arxiv on: 16 Apr 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Neural and Evolutionary Computing (cs.NE)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper introduces an interpolating neural network (INN), which leverages interpolation theory and tensor decomposition to advance data training, partial differential equation solving, and parameter calibration in engineering software. INN is shown to offer orders of magnitude fewer trainable/solvable parameters for comparable model accuracy compared to traditional multi-layer perceptron (MLP) or physics-informed neural networks (PINN). The authors demonstrate the effectiveness of INN by rapidly constructing an accurate surrogate model of Laser Powder Bed Fusion (L-PBF) heat transfer simulation, achieving sub-10-micrometer resolution for a 10 mm path in under 15 minutes on a single GPU. This breakthrough has significant implications for all domains essential to engineering software. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper is about using artificial intelligence to make computer programs better and faster. It’s like going from an old car to a new one – the new one can do more things and do them faster. The problem is that it’s hard to make these new programs work well, especially when they have to solve complex problems like how heat moves in metal manufacturing. To fix this, the authors created a new kind of computer program called an interpolating neural network (INN). It’s really good at solving these kinds of problems and can do it much faster than other methods. |
Keywords
» Artificial intelligence » Neural network
