当前位置:
X-MOL 学术
›
arXiv.cs.MA
›
论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Sparse Training Theory for Scalable and Efficient Agents
arXiv - CS - Multiagent Systems Pub Date : 2021-03-02 , DOI: arxiv-2103.01636 Decebal Constantin Mocanu, Elena Mocanu, Tiago Pinto, Selima Curci, Phuong H. Nguyen, Madeleine Gibescu, Damien Ernst, Zita A. Vale
arXiv - CS - Multiagent Systems Pub Date : 2021-03-02 , DOI: arxiv-2103.01636 Decebal Constantin Mocanu, Elena Mocanu, Tiago Pinto, Selima Curci, Phuong H. Nguyen, Madeleine Gibescu, Damien Ernst, Zita A. Vale
A fundamental task for artificial intelligence is learning. Deep Neural
Networks have proven to cope perfectly with all learning paradigms, i.e.
supervised, unsupervised, and reinforcement learning. Nevertheless, traditional
deep learning approaches make use of cloud computing facilities and do not
scale well to autonomous agents with low computational resources. Even in the
cloud, they suffer from computational and memory limitations, and they cannot
be used to model adequately large physical worlds for agents which assume
networks with billions of neurons. These issues are addressed in the last few
years by the emerging topic of sparse training, which trains sparse networks
from scratch. This paper discusses sparse training state-of-the-art, its
challenges and limitations while introducing a couple of new theoretical
research directions which has the potential of alleviating sparse training
limitations to push deep learning scalability well beyond its current
boundaries. Nevertheless, the theoretical advancements impact in complex
multi-agents settings is discussed from a real-world perspective, using the
smart grid case study.
中文翻译:
可扩展高效代理的稀疏训练理论
人工智能的一项基本任务是学习。事实证明,深度神经网络可以完美地应对所有学习范例,即监督学习,无监督学习和强化学习。然而,传统的深度学习方法利用云计算工具,无法很好地扩展到具有低计算资源的自治代理。即使在云中,它们也受到计算和内存限制的困扰,并且无法用于为具有数十亿个神经元网络的智能体建模足够大的物理世界。在过去的几年中,新兴的稀疏训练主题解决了这些问题,该主题从头开始训练稀疏网络。本文讨论了稀疏训练的最新技术,它的挑战和局限性,同时引入了两个新的理论研究方向,有可能缓解稀疏训练的局限性,从而将深度学习可扩展性远远超出其当前范围。尽管如此,使用智能电网案例研究还是从现实世界的角度讨论了理论进步对复杂多智能体设置的影响。
更新日期:2021-03-03
中文翻译:
可扩展高效代理的稀疏训练理论
人工智能的一项基本任务是学习。事实证明,深度神经网络可以完美地应对所有学习范例,即监督学习,无监督学习和强化学习。然而,传统的深度学习方法利用云计算工具,无法很好地扩展到具有低计算资源的自治代理。即使在云中,它们也受到计算和内存限制的困扰,并且无法用于为具有数十亿个神经元网络的智能体建模足够大的物理世界。在过去的几年中,新兴的稀疏训练主题解决了这些问题,该主题从头开始训练稀疏网络。本文讨论了稀疏训练的最新技术,它的挑战和局限性,同时引入了两个新的理论研究方向,有可能缓解稀疏训练的局限性,从而将深度学习可扩展性远远超出其当前范围。尽管如此,使用智能电网案例研究还是从现实世界的角度讨论了理论进步对复杂多智能体设置的影响。