arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1908.10714cs.LGcs.NEstat.ML
收藏

深度神经网络的自动化体系结构设计

Automated Architecture Design for Deep Neural Networks

Jacobs University Bremen(不来梅雅各布大学)

Steven Abreu

摘要:

近年来,机器学习取得了巨大的进步,并受到了公众的广泛关注。虽然我们离设计一个完整的人工智能代理还很远,但机器学习已经给我们带来了许多应用,在这些应用中,计算机非常好地解决了人类的学习任务。这些进展大部分来自机器学习中的一个最新趋势,称为深度学习。深度学习模型负责机器学习的许多最先进的应用。尽管取得了成功,但深度学习模型很难训练,很难理解,而且往往非常复杂,只能在非常大的GPU集群上进行训练。在使神经网络能够有效学习方面已经做了大量的工作。然而,这种神经网络的设计和架构通常通过试错和专家知识手动完成。本论文研究了不同的方法,现有的和新的,自动化的深度前馈神经网络的设计,试图创建具有良好的性能,消除了负担,决定一个架构,使其更有效地设计和训练这样的深度网络的复杂性较低的模型。

英文摘要:

Machine learning has made tremendous progress in recent years and received large amounts of public attention. Though we are still far from designing a full artificially intelligent agent, machine learning has brought us many applications in which computers solve human learning tasks remarkably well. Much of this progress comes from a recent trend within machine learning, called deep learning. Deep learning models are responsible for many state-of-the-art applications of machine learning. Despite their success, deep learning models are hard to train, very difficult to understand, and often times so complex that training is only possible on very large GPU clusters. Lots of work has been done on enabling neural networks to learn efficiently. However, the design and architecture of such neural networks is often done manually through trial and error and expert knowledge. This thesis inspects different approaches, existing and novel, to automate the design of deep feedforward neural networks in an attempt to create less complex models with good performance that take away the burden of deciding on an architecture and make it more efficient to design and train such deep networks.

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。

↑