基于Cramer-Wold度量的非线性ICA
Non-linear ICA based on Cramer-Wold metric
Jagiellonian University（雅盖隆大学）
摘要：
非线性声源分离是一个具有挑战性的开放性问题，有许多应用。我们扩展了最近提出的对抗性非线性ICA（ANICA）模型，并引入Cramer-Wold ICA（CW-ICA）。与ANICA相比，我们使用一个简单的，封闭形式的优化目标，而不是一个基于独立性的措施。我们的研究结果表明，CW-ICA实现了与ANICA相当的结果，同时无需对抗训练。
英文摘要：
Non-linear source separation is a challenging open problem with many applications. We extend a recently proposed Adversarial Non-linear ICA (ANICA) model, and introduce Cramer-Wold ICA (CW-ICA). In contrast to ANICA we use a simple, closed--form optimization target instead of a discriminator--based independence measure. Our results show that CW-ICA achieves comparable results to ANICA, while foregoing the need for adversarial training.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
