Contents

Course information, requirements and reference

from IPython.display import IFrame

IFrame(src="https://cdnapisec.kaltura.com/p/2356971/sp/235697100/embedIframeJs/uiconf_id/41416911/partner_id/2356971?iframeembed=true&playerId=kaltura_player&entry_id=1_b5pq3bnx&flashvars[streamerType]=auto&flashvars[localizationCode]=en&flashvars[leadWithHTML5]=true&flashvars[sideBarContainer.plugin]=true&flashvars[sideBarContainer.position]=left&flashvars[sideBarContainer.clickToClose]=true&flashvars[chapters.plugin]=true&flashvars[chapters.layout]=vertical&flashvars[chapters.thumbnailRotator]=false&flashvars[streamSelector.plugin]=true&flashvars[EmbedPlayer.SpinnerTarget]=videoHolder&flashvars[dualScreen.plugin]=true&flashvars[hotspots.plugin]=1&flashvars[Kaltura.addCrossoriginToIframe]=true&&wid=1_131rzy9w",width='800', height='500')
Please access the video via one of the following two ways

Course Instructor and Assistants

Course Description

Class time (recorded videos):

  • lectures providing motivations, description and mathematical analysis of deep learning algorithms

  • hands-on coding exercises for python programming for deep learning algorithms

Detailed course materials and forms:

  • pre-recorded video lectures

  • typed lecture notes

  • live discussions

  • programming subroutines

  • theoretical and practical exercises

Interactive programming environment:

  • Click the “Binder” icon under Rocket icon: rocket

  • !!! Attention: the interactive programming environment won’t save your code

Course Description and Syllabus

Main topics include:

  • Basics of machine learning and probability

  • Logistic regression and support vector machine

  • Gradient descent method and training algorithms

  • Polynomial approximation and Weierstrass theorem

  • Linear finite element spaces

  • Deep neural networks and mathematical properties

  • Convolutional neural networks

  • Multigrid methods and MgNet

  • PyTorch and deep learning for image classification

  • Other applications

  • Syllabus

Grading Policies

  • Homework and programing assignments (collecting every week) (40%)

  • midterm exam (20%)

  • final projects and exam (40%)

Prerequisites, References and Resources

Prerequisites

  • Linear algebra;

  • Multi-variable calculus;

  • Some programming experiences are helpful. For those who are not familiar with Python, see tutorials in:

References and resources:

Xu J. Deep Neural Networks and Multigrid Methods, (Lecture Notes at Penn State), 2019. Goodfellow I, Bengio Y, Courville A. Deep learning. MIT press, 2016. Friedman J, Hastie T, Tibshirani R. The elements of statistical learning. New York: Springer series in statistics, 2001. CS231n (Stanford): http://cs231n.stanford.edu