Coffee with Clusterone Webinar Series
--
Upcoming Webinars
Our Coffee with Clusterone webinars last about one hour. They offer a brief introduction, a demonstration of the subject matter and a Q & A session at the end.
To be notified of upcoming webinars, subscribe[HERE].
May 21, 2018. 9am PDT
Machine Learning with Google Brain’s Tensor2Tensor. Special guest, Ryan Sepassi, Senior Research Engineer at Google Brain
Tensor2Tensor is a library of machine learning models and datasets as well as a framework for iterative reproducible research. It is built, maintained, and used by members of the Google Brain team, and is also open-source at http://github.com/tensorflow/tensor2tensor with over 3.5k stars, 68 contributors, 51 releases, and nearly 1k forks. Ryan will give a brief overview of Tensor2Tensor and demo training, evaluating, and making predictions from a translation model and show what would be required to add your own dataset and modify the model.
Register here: http://bit.ly/sepassi-google
Ryan is a Senior Research Engineer on the Google Brain team. He co-authored and co-maintains Tensor2Tensor and contributes to TensorFlow. He has worked on many projects at Brain, most recently publishing a paper on large-scale summarization (Generating Wikipedia by Generating Long Sequences https://arxiv.org/abs/1801.10198).
Past Webinars
Missed a past webinar or want to revisit the content? No problem! Our webinars are also available on YouTube, so check them out at your leisure.
April 19, 2018: How to Speed up Training with distributed TensorFlow with Malo Marrec
This webinar discusses the Clusterone platform and how to speed up your machine learning training with distributed TensorFlow.
How to Tune Neural Networks with Mohsen Hejrati, PhD. in Computer Vision and Machine Learning
During this webinar, our CEO and co-founder, Mohsen Hejrati (PhD, Machine Learning) will present the tools and approaches for understanding and tuning hyperparameters in a systematic way.
During this webinar, our CEO and co-founder, Mohsen Hejrati (PhD, Machine Learning) will present the tools and approaches for understanding and tuning hyperparameters in a systematic way.
