Past Meetup

Elizabeth Ramirez on A New Approach to Linear Filtering and Prediction Problems

This Meetup is past

152 people went

Two Sigma

101 Ave. of the Americas, 23rd Fl. J · New York

How to find us

Cross Streets: Watt and Grand. Note: Please make sure you’re signed-up for the meetup, including your first and last name. Without this info you won’t be allowed into the building by security.

Location image of event venue

Details

It's with great pleasure to announce that we'll be hosting Elizabeth Ramirez, a senior software engineer at The New York Times (http://www.nytimes.com/) and M.S. candidate in Applied Mathematics at Columbia University (http://apam.columbia.edu/). She'll be presenting on a classic: A New Approach to Linear Filtering and Prediction Problems (https://www.cs.unc.edu/~welch/kalman/media/pdf/Kalman1960.pdf) by Rudolf Kálmán. Kálmán, who passed away in July (http://hungarytoday.hu/news/renowned-hungarian-scientis-rudolf-kalman-dies-aged-86-46732), was a luminary (http://ethw.org/Rudolf_E._Kalman) who shaped the field of modern control theory (https://en.wikipedia.org/wiki/Control_theory#Modern_control_theory).

There are many Kalman Filter tutorials to be found on the web, such as http://www.bzarg.com/p/how-a-kalman-filter-works-in-pictures/ . Elizabeth gave a great talk at PyCon (https://youtu.be/k_MpfzMc9PU) this year on implementing a discrete Kalman Filter in Python:

https://www.youtube.com/watch?v=k_MpfzMc9PU

Intro

The Kalman Filter (https://en.wikipedia.org/wiki/Kalman_filter) is a prediction-correction algorithm named after Rudolf E. Kálmán (https://en.wikipedia.org/wiki/Rudolf_E._K%C3%A1lm%C3%A1n) [masked]), by which we calculate recursively a dynamical system state at time t_{k} using state at previous time u_{k-1} and new information b_{k} only. This technique is presented as a generalization of the least squares model for problems with varying mean and additive noise.

The Kalman Filter was first applied in the 1960s to the problem of trajectory estimation for NASA's Apollo space program and incorporated into their space navigation computer. It is also used in the guidance and navigation systems of the NASA Space Shuttle and the attitude control and navigation systems of the International Space Station. In other words, it is mostly used for positioning and navigation systems, but it can be generalized to any time series under suitable conditions.

Rudolf Kálmán recently passed away, and I thought it was a good idea to honor his memory at Papers We Love by presenting his original paper published in 1960, "A New Approach to Linear Filtering and Prediction Problems (https://www.cs.unc.edu/~welch/kalman/media/pdf/Kalman1960.pdf)", aka Kalman Filter.

Bio

Elizabeth Ramirez (@eramirem (https://twitter.com/eramirem)) is a Senior Software Engineer at The New York Times (http://www.nytimes.com/) and M.S. candidate in Applied Mathematics at Columbia University (http://apam.columbia.edu/). She likes analytical and numerical methods for solving partial differential equations, and all things space.

------------------------------------------------------------------------

TwoSigma (https://www.twosigma.com/) - Platinum Sponsor of the New York chapter

------------------------------------------------------------------------

Details

Doors open at 7 pm; the presentation will begin at 7:30 pm; and, yes, there will be refreshments of all kinds and pizza.

A little different than previous PWLs, you'll have to check-in with security with your Name/ID. Definitely sign-up if you’re going to attend–unfortunately people whose names aren’t entered into the security system in advance won’t be allowed in.

After Elizabeth presents the paper, we will open up the floor to discussion and questions.

We hope that you'll read the paper before the meetup, but don't stress if you can't. If you have any questions, thoughts, or related information, please visit #pwlnyc (https://paperswelove.slack.com/messages/pwlnyc/) on slack (http://papersweloveslack.herokuapp.com/), our GitHub repository (https://github.com/papers-we-love/papers-we-love), where you can also find the paper (https://github.com/papers-we-love/papers-we-love/blob/master/data_fusion/a-new-approach-to-linear-filtering-and-prediction-problems.pdf), or add to the discussion on this event's thread.

Additionally, if you have any papers you want to add to the repository above (papers that you love!), please send us a pull request (https://github.com/papers-we-love/papers-we-love/pulls). Also, if you have any ideas/questions about this meetup or the Papers-We-Love org, just open up an issue.

September's meetup is sponsored by