CORNN (Continuous Optimisation of Regression tasks using Neural Networks)

CORNN数据集是由南非大学的研究团队创建，专注于神经网络回归任务的连续优化。该数据集包含324个问题实例，涵盖了不同维度和难度的回归问题，适用于评估任何连续黑盒优化算法的性能。数据集的创建过程涉及使用54个二维函数作为回归拟合任务的基础，并通过不同的神经网络模型生成问题实例。CORNN数据集的应用领域主要集中在优化算法性能的基准测试，旨在解决高维度优化问题，特别是在神经网络训练中的应用。

The CORNN dataset was developed by a research team at the University of South Africa, with a core focus on continuous optimization for neural network regression tasks. It encompasses 324 problem instances covering regression tasks of varying dimensions and difficulty levels, making it suitable for evaluating the performance of any continuous black-box optimization algorithm. The dataset construction process adopted 54 two-dimensional functions as the basis for regression fitting tasks, and generated problem instances via different neural network models. The primary application scenario of the CORNN dataset is benchmarking the performance of optimization algorithms, aiming to solve high-dimensional optimization problems, especially for applications in neural network training.