arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2102.04883physics.comp-phcond-mat.dis-nncs.LG
收藏

机器学习科学导论

Introduction to Machine Learning for the Sciences

University of Zurich(苏黎世大学);Kavli Institute of Nanoscience(卡夫利纳米科学研究所);Delft University of Technology(代尔夫特理工大学);ETH Zurich(苏黎世联邦理工学院)

Titus Neupert, Mark H Fischer, Eliska Greplova, Kenny Choo, M. Michael Denner

摘要:

这是一门专门为STEM学生开发的机器学习入门课程。我们的目标是为感兴趣的读者提供在自己的项目中使用机器学习的基础知识,并熟悉术语,作为进一步阅读相关文献的基础。在这些课堂讲稿中,我们讨论了监督学习、无监督学习和强化学习。这些笔记首先阐述了没有神经网络的机器学习方法,例如主成分分析,t-SNE,聚类,以及线性回归和线性分类器。我们继续介绍基本和高级神经网络结构,如密集前馈和传统神经网络,递归神经网络,限制玻尔兹曼机,(变分)自动编码器,生成对抗网络。潜在的空间表示和使用的例子做梦和对抗性攻击的可解释性问题进行了讨论。最后一节专门介绍强化学习,在那里我们介绍了价值函数和策略学习的基本概念。

英文摘要:

This is an introductory machine-learning course specifically developed with STEM students in mind. Our goal is to provide the interested reader with the basics to employ machine learning in their own projects and to familiarize themself with the terminology as a foundation for further reading of the relevant literature. In these lecture notes, we discuss supervised, unsupervised, and reinforcement learning. The notes start with an exposition of machine learning methods without neural networks, such as principle component analysis, t-SNE, clustering, as well as linear regression and linear classifiers. We continue with an introduction to both basic and advanced neural-network structures such as dense feed-forward and conventional neural networks, recurrent neural networks, restricted Boltzmann machines, (variational) autoencoders, generative adversarial networks. Questions of interpretability are discussed for latent-space representations and using the examples of dreaming and adversarial attacks. The final section is dedicated to reinforcement learning, where we introduce basic notions of value functions and policy 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。

↑