arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1809.01587cs.HCcs.AIcs.LGstat.ML
收藏

GAN Lab:使用交互式视觉实验理解复杂的深度生成模型

GAN Lab: Understanding Complex Deep Generative Models using Interactive Visual Experimentation

Georgia Institute of Technology(佐治亚理工学院);Google Brain(谷歌大脑)

Minsuk Kahng, Nikhil Thorat, Duen Horng Chau, Fernanda Viégas, Martin Wattenberg

摘要:

最近在深度学习方面取得的成功引起了从业者和学生的极大兴趣,激发了许多人学习这项新技术。虽然已经成功开发了可视化和交互式方法来帮助人们更轻松地学习深度学习,但大多数现有工具都专注于更简单的模型。在这项工作中,我们提出了GAN Lab,这是第一个交互式可视化工具,专为非专家学习和实验生成对抗网络(GANs),这是一类流行的复杂深度学习模型。通过GAN Lab,用户可以交互式地训练生成模型,并可视化动态训练过程的中间结果。GAN Lab紧密集成了一个模型概览图,它总结了GAN的结构,以及一个分层分布视图,帮助用户解释子模型之间的相互作用。GAN实验室引入了新的交互式实验功能,用于学习复杂的深度学习模型,例如在多个抽象级别上进行分步训练,以了解复杂的训练动态。GAN Lab使用TensorFlow.js实现,任何人都可以通过现代Web浏览器访问,无需安装或专用硬件,克服了部署深度学习交互式工具的重大实际挑战。

英文摘要:

Recent success in deep learning has generated immense interest among practitioners and students, inspiring many to learn about this new technology. While visual and interactive approaches have been successfully developed to help people more easily learn deep learning, most existing tools focus on simpler models. In this work, we present GAN Lab, the first interactive visualization tool designed for non-experts to learn and experiment with Generative Adversarial Networks (GANs), a popular class of complex deep learning models. With GAN Lab, users can interactively train generative models and visualize the dynamic training process's intermediate results. GAN Lab tightly integrates an model overview graph that summarizes GAN's structure, and a layered distributions view that helps users interpret the interplay between submodels. GAN Lab introduces new interactive experimentation features for learning complex deep learning models, such as step-by-step training at multiple levels of abstraction for understanding intricate training dynamics. Implemented using TensorFlow.js, GAN Lab is accessible to anyone via modern web browsers, without the need for installation or specialized hardware, overcoming a major practical challenge in deploying interactive tools for deep learning.

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。

↑