![[Uber Marketplace] An Introduction Chintan Turakhia @UberEngineering](https://i.ytimg.com/vi/cdNn44JYtNw/maxresdefault.jpg)
Uploaded October 2018 | Updated September 2026, 2 weeks ago
In this presentation from a May 2018 meetup, engineering manager Chintan Turakhia discusses how the Uber Marketplace leverages machine learning to deliver improved rider, driver, and eater experiences.
In this presentation from a May 2018 meetup, engineering manager Chintan Turakhia discusses how the Uber Marketplace leverages machine learning to deliver improved rider, driver, and eater experiences.
![[Uber Marketplace] An Introduction Chintan Turakhia](https://i.ytimg.com/vi/cdNn44JYtNw/mqdefault.jpg "[Uber Marketplace] An Introduction Chintan Turakhia
In this presentation from a May 2018 meetup, engineering manager Chintan Turakhia discusses how the Uber Marketplace leverages machine learning to deliver improved rider, driver, and eater experiences.")
![[XGBoost Meetup] Introduction to the XGBoost Community Nan Zhu & Philip Cho](https://i.ytimg.com/vi/dsqwIRrdcTA/mqdefault.jpg "[XGBoost Meetup] Introduction to the XGBoost Community Nan Zhu & Philip Cho
During a January 2019 XGBoost meetup hosted at Ubers SF office, Uber software engineer Nan Zhu and Amazon software engineer Philip Cho discuss the history and development of XGBoost, an open source software library that provides a gradient boosting framework for C++, Java, Python, R, and Julia.")
![[Uber Open Source] Profile Spark Applications at Scale Bo Yang](https://i.ytimg.com/vi/fCTdbX-mG2I/mqdefault.jpg "[Uber Open Source] Profile Spark Applications at Scale Bo Yang
During a June 2018 Open Source Meetup at our Seattle office, senior software engineer Bo Yang discusses how Ubers open source JVM Profiler enables us to profile Spark applications at scale across our microservices.")
![[Uber Seattle] Horovod: Distributed Deep Learning on Spark](https://i.ytimg.com/vi/fZ9P1v1jtFM/mqdefault.jpg "[Uber Seattle] Horovod: Distributed Deep Learning on Spark
During this April 2019 meetup, Uber engineer Travis Addair introduces the concepts that make Horovod work, and walks through how to make use of Horovod on Spark to add distributed training to machine learning pipelines. Horovod is a distributed training framework for TensorFlow, PyTorch, Keras, and MXNet. Scaling to hundreds of GPUs, Horovod can reduce training time from hours to minutes with just a handful of lines added to existing single-GPU training processes.")
![[WiSDOM] An Intriguing Failing of Convolutional NNs & the CoordConv Solution Rosanne Liu](https://i.ytimg.com/vi/gMGL-shl3P8/mqdefault.jpg "[WiSDOM] An Intriguing Failing of Convolutional NNs & the CoordConv Solution Rosanne Liu
During an October 2018 meetup, Uber WiSDOM (Women in Statistics, Data Optimization, and Machine Learning) member & Uber AI researcher Rosanne Liu discuses how convolutional neural networks often fail to complete seemingly trivial tasks and introduces a novel solution to to improve their performance: the CoordConv layer.")
![[Go NYC] End-to-End Testing with Golang Adrian Witas](https://i.ytimg.com/vi/hfVAXTi39UA/mqdefault.jpg "[Go NYC] End-to-End Testing with Golang Adrian Witas
During an October 2018 Go Language NYC meetup, Adrian Witas, VP Software Architect at Viant, discusses how to conduct end-to-end testing with Go.")
![[Uber Mobility] Profiler Performance - Brian Attwell](https://i.ytimg.com/vi/ime9EBuvxDA/mqdefault.jpg "[Uber Mobility] Profiler Performance - Brian Attwell
In this presentation during a March 2018 meetup, staff engineer Brian Attwell introduces Nanoscope, a method tracing tool for Android that improves app performance.
Read the Eng Blog article: https://eng.uber.com/nanoscope/")
![[Visualization Nights] Designing for Complex Data Visualization - Elijah Meeks](https://i.ytimg.com/vi/iqWSJLFa9hg/mqdefault.jpg "[Visualization Nights] Designing for Complex Data Visualization - Elijah Meeks
While Netflix uses simple charts in various applications across, there are analytical views that require complex charts. During our June 2018 Visualization Night, Netflixs Elijah Meeks explores the design and implementation of network visualization to represent flow of Netflix users through different aspects of the product.")
![[Distributed Tracing NYC] Tracing @ Facebook Edison Gao & Michael Bevilacqua-Linn](https://i.ytimg.com/vi/j6no6JozkZU/mqdefault.jpg "[Distributed Tracing NYC] Tracing @ Facebook Edison Gao & Michael Bevilacqua-Linn
During an October 2018 Distributed Tracing NYC meetup, Facebook engineers Edison Gao & Michael Bevilacqua-Linn offer a brief overview of Facebooks distributed tracing system, Canopy, and how/why it differs from the more standard OpenTracing/Dapper model.")
