用LaTeX写深度学习库，编译时自动训练模型并出结果。
NeuRaLaTeX: A machine learning library written in pure LaTeX
- 在LaTeX文档中定义网络结构和训练流程，编译即执行
- 48小时编译完成100点螺旋数据集上的两层MLP训练与评估
- 首次实现纯LaTeX深度学习库，适合追求极致可复现的科研者
本文介绍NeuRaLaTeX，据我们所知是首个完全用LaTeX编写深度学习库。在LaTeX文档中可指定神经网络架构、损失函数、训练数据生成或加载方式，以及超参数和实验配置。编译时，LaTeX编译器将自动生成或加载训练数据，训练网络，运行实验，并生成图表。本文使用随机生成的100点螺旋数据集，训练一个两层MLP，在另一组随机螺旋数据上评估，生成结果图表与表格。论文编译耗时48小时，且NeuRaLaTeX全部源码均包含于论文源码中。我们提出两个新指标：写作在LaTeX中的比例（WIL）衡量库代码纯LaTeX程度，论文源码中方法实现占比（SCOMISCOP）衡量论文内实现比例。我们在两项指标上均达到当前最优，优于ResNet、Transformer论文及PyTorch、TensorFlow库。源码、文档、视频、加密货币骗局信息及投资邀请见https://www.neuralatex.com
原文摘要 · Abstract (English)
In this paper, we introduce NeuRaLaTeX, which we believe to be the first deep learning library written entirely in LaTeX. As part of your LaTeX document you can specify the architecture of a neural network and its loss functions, define how to generate or load training data, and specify training hyperparameters and experiments. When the document is compiled, the LaTeX compiler will generate or load training data, train the network, run experiments, and generate figures. This paper generates a random 100 point spiral dataset, trains a two layer MLP on it, evaluates on a different random spiral dataset, produces plots and tables of results. The paper took 48 hours to compile and the entire source code for NeuRaLaTeX is contained within the source code of the paper. We propose two new metrics: the Written In Latex (WIL) metric measures the proportion of a machine learning library that is written in pure LaTeX, while the Source Code Of Method in Source Code of Paper (SCOMISCOP) metric measures the proportion of a paper's implementation that is contained within the paper source. We are state-of-the-art for both metrics, outperforming the ResNet and Transformer papers, as well as the PyTorch and Tensorflow libraries. Source code, documentation, videos, crypto scams and an invitation to invest in the commercialisation of NeuRaLaTeX are available at https://www.neuralatex.com
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。