摘要
由机器人与机器学习每日新闻的新闻记者兼新闻编辑-研究人员详细介绍了计算智能的新数据。根据NewsRx记者在日本神奈川的新闻报道，研究表明，"使用深度学习算法直接优化船体设计的期望越来越高，因为它几乎是在瞬间为设计者提出优化方向，而不依赖于复杂的、耗时的和昂贵的流体动力学模拟。"这项研究的资助者包括日本海洋联合公司。新闻记者从横滨国立大学的研究中得到一句话：“在这项研究中，我们提出了一种基于GAN的三维船体设计优化方法，通过训练一个单独的模型来预测船舶性能指标，消除了对水动力模拟的依赖。”我们使用相对论平均鉴别器来获得关于异常设计的更好反馈，我们为发生器增加了两个新的损失函数：一个限制设计变异性，另一个利用性能估计模型的反馈来设置改进TARG ETS。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Researchers detail new data in computa tional intelligence. According to news reporting from Kanagawa, Japan, by NewsRx journalists, research stated, “The direct optimization of ship hull designs usi ng deep learning algorithms is increasingly expected, as it proposes optimizatio n directions for designers almost instantaneously, without relying on complex, t ime-consuming, and expensive hydrodynamic simulations.” Funders for this research include Japan Marine United Corporation. The news journalists obtained a quote from the research from Yokohama National U niversity: “In this study, we proposed a GAN-based 3D ship hull design optimizat ion method. We eliminated the dependence on hydrodynamic simulations by training a separate model to predict ship performance indicators. Instead of a standard discriminator, we applied a relativistic average discriminator to obtain better feedback regarding the anomalous designs. We add two new loss functions for the generator: one restricts design variability, and the other sets improvement targ ets using feedback from the performance estimation model.”
NETL
NSTL