October 8, 2019

187 words 1 min read

Open Standards for Machine Learning Deployment

Open Standards for Machine Learning Deployment

Machine learning is typically viewed as simply training a model on data. However, the last mile of deploying models to production systems is often overlooked and yet is one of the most critical aspe …

Talk Title Open Standards for Machine Learning Deployment
Speakers Animesh Singh (Chief Architect and Program Director, IBM), Hou Gang, Liu (Advisory Software Developer, IBM)
Conference KubeCon + CloudNativeCon
Conf Tag
Location Shanghai, China
Date Jun 23-26, 2019
URL Talk Page
Slides Talk Slides
Video

Machine learning is typically viewed as simply training a model on data. However, the “last mile” of deploying models to production systems is often overlooked and yet is one of the most critical aspects of real-world machine learning systems. Despite this, currently there are few widely accepted, open and standard solutions available that cover deployment of end-to-end ML pipelines.In this talk, I explore the current state of ML deployment using open-source, standardized formats. The talk will cover the various available options, including PMML, PFA and ONNX, and how these fit in with the most popular and widely used ML libraries (including scikit-learn, Spark ML, TensorFlow, Keras and PyTorch).

comments powered by Disqus