(Thanks for forwarding Sheng). Hi Vartika, I've uploaded downloadable video link here: https://www.dropbox.com/s/s1wvr2184tjc0ca/autogluon%20-%20MXNet%20Day.mp4?dl=0
Let me know if you need anything else. Thanks, Jonas PS. Here's a description in case you need it: AutoGluon: Open-source AutoML for Text, Image, and Tabular Data AutoGluon is an open-source software toolkit to automate machine learning (ML) on image, text, and tabular data (built on top of MXNet). With a couple lines of Python code, anybody can translate their raw data into highly accurate predictions, regardless of their ML expertise. In comprehensive benchmarks over 50 tabular datasets, AutoGluon produced significantly more accurate models (given the same runtime/compute) than other popular AutoML tools like TPOT, H2O, AutoWEKA, auto-sklearn, Google AutoML Tables. In two prominent Kaggle competitions, AutoGluon outperformed 99% of human data science teams after just being run for 4 hours on the raw tabular data. In comparisons with human data scientists on 4 image classification competitions from Kaggle, AutoGluon consistently ranked around the top 10%. AutoGluon has also been used to win a number of internal prediction competitions at Amazon, and is being used in production for multiple applications. This talk describes how AutoGluon achieves such strong predictive performance through state-of-the-art deep learning, hyperparameter-optimization, stack ensembling, and other modelling techniques. On 12/10/20, 12:39 PM, "Sheng Zha" <[email protected]> wrote: CAUTION: This email originated from outside of the organization. Do not click links or open attachments unless you can confirm the sender and know the content is safe. +Jonas On Thu, Dec 10, 2020 at 2:05 AM Vartika Singh <[email protected]> wrote: > > Hello Mueller, > > Apologies for the late response. > > Our agenda is full. However, we were hoping that you could make your talk available to us as a recording of 15-20 minutes and send a link to the downloadable video by end of Friday? > > We will not be able to slot you in the agenda, however we can make the video available for attendees to view. We will also create a slack channel specifically for your talk where folks can ask questions to yoou directly. > > Would this be acceptable to you? If yes, please let us know and send the link to video recording, mp4, by end of Friday. > > Warm Regards > Vartika > > On 2020/12/03 01:18:10, "Mueller, Jonas" <[email protected]> wrote: > > Hi I just wanted to follow-up and make sure this has been received? > > > > Thanks, > > Jonas > > > > From: "Mueller, Jonas" <[email protected]> > > Date: Friday, November 20, 2020 at 6:30 PM > > To: "[email protected]" <[email protected]> > > Cc: "Ye, Wen-ming" <[email protected]> > > Subject: Talk Abstract for MXNet day: AutoGluon > > > > Hi, I’m writing to submit an abstract for a proposed talk for Apache MXNet day. > > > > Thanks for your consideration! > > Jonas > > > > Talk Title: AutoGluon: Powerful and Easy-to-use AutoML for Text, Image, and Tabular Data > > > > Talk Abstract: > > > > AutoGluon<https://github.com/awslabs/autogluon/> is an open-source software toolkit to automate machine learning (ML) on image, text, and tabular data (built on top of MXNet). With a couple lines of Python code, anybody can translate their raw data into highly accurate predictions, regardless of their ML expertise. In comprehensive benchmarks<https://arxiv.org/pdf/2003.06505.pdf> over 50 datasets, AutoGluon produced significantly more accurate models (given the same runtime/compute) than other popular AutoML tools like TPOT, H2O, AutoWEKA, auto-sklearn, Google AutoML Tables. In two prominent Kaggle competitions with tabular data, AutoGluon outperformed 99% of human data science teams after just being run for 4 hours on the raw data. In comparisons with human data scientists on 4 image classification competitions from Kaggle<https://medium.com/@zhanghang0704/image-classification-on-kaggle-using-autogluon-fc896e74d7e8>, AutoGluon consistently ranked around the top 10%. AutoGluon > has also been used to win a number of internal prediction competitions at Amazon, and is being used in production for multiple applications. This talk describes how AutoGluon achieves such strong predictive performance through state-of-the-art deep learning, hyperparameter-optimization, stack ensembling, and other modelling techniques. > > > > --------------------------------------------------------------------- > To unsubscribe, e-mail: [email protected] > For additional commands, e-mail: [email protected] >
