Great time presenting a tutorial on Deep Generative Models at the Deep Learning for Science School (dl4sci-school.lbl.gov) at Berkeley! Video: youtube.com/watch?v=lCYdaa… Slides: drive.google.com/file/d/1dKc8f6…

I will regret this slide in the morning.

Great work!

Very impressive presentation.

#ISFConf2020 wraps up for us with a well-attended "deep learning for forecasting" workshop together with WhoIsElla material is here: lostella.github.io/ISF-2020-Deep-… including a notebook with #gluonts & #pytorch

Good.

When I introduce my research in the party, someone else also say 'can you predict the stock market and we all get rich'.

The first snow in UK at Christmas Day. Merry Christmas and Happy New Year to u.

Here are my top-three tips on academic publishing: 1) Work on what excites you. 2) Understand your skills and limitations; utilise your network. 3) Don't be afraid to submit your work (even if the result is rejection); use the comments from the review team to improve your paper.

Another snow in UK. I am so excited

Can't wait to read it and learn from it.

Home made Chinese sausage for the coming Chinese New Year!

Joint work with Yanfei Kang Yun Bai We associate the contents in M5 Kaggle with those top solutions in M5 competition with topic modeling and social network analysis.

#ISF2022 finally got my part of my PhD work presented. Deep learning for VAR modelling.

Wonderful experience at Cambridge machine learning summer school and many thanks to CambridgeEllisUnit Cambridge University Jose Miguel Hernández-Lobato Petar Veličković for their organization and lectures.

Our boy, Freddy, went missing yesterday at Bathampton, Bath, UK. Please, help us find him.

To improve computation efficiency in current big data settings，instead of using information criteria for ETS model selection，we directly predict appropriate ETS model component forms for a given time series using pretrained classifiers. sciencedirect.com/science/articl…

Thanks for mentioning it. In this study, we propose a new approach called DeepVARwT that employs deep learning methodology for maximum likelihood estimation of the trend and the dependence structure at the same time.

Do you want to learn more about forecast combinations? Read this outstanding new review paper by Xiaoqian Wang @robjhyndman Feng Li Yanfei Kang published at the International Journal of Forecasting. doi.org/10.1016/j.ijfo…

"My main job is to develop the musical abilities of machines to enable functions such as music fingerprinting, personalized recommendation, and voice tuning," shares #TsinghuaRen alumna Guo Yichen, a musical algorithm engineer at Huawei who also enjoys playing in her own band.