Indico to Speak on Machine Learning at 2018 ODSC East

Effective Transfer Learning for NLP


BOSTON, April 24, 2018 (GLOBE NEWSWIRE) -- Indico machine learning architect and co-founder, Madison May will be a featured presenter at the 2018 Open Data Science Conference (ODSC) taking place May 1 - 4 at the Boston Convention Center. May will deliver a technical talk on transfer learning and how it can be used to deliver efficiencies in machine learning on text-based content. May has played a key role in the development of Indico’s enterprise AI solution for unstructured content and designed and built an NLP system at Fetchnotes. He was also an active open source contributor to projects like Python3, Pylearn2, and Theano.

Indico will also be a sponsor at the event, showcasing its enterprise AI solution. The platform enables users to work with much smaller sets of data to create customized models for automating manual, document-based business processes and extracting valuable insights from existing unstructured enterprise data. Indico will be located at Sponsor Table #30, right across from room 210C in Southwest Prefunction area on Level 2 of the Boston Convention Center.

ODSC East 2018 is one of the largest applied data science conferences in the world. Speakers include some of the core contributors to the industry’s leading open source tools, libraries, and languages. Attendees can learn the latest AI & data science topics, tools, and languages from some of the best and brightest minds in the field.

Session Details: 
Effective Transfer Learning for NLP
May 4th, 11:55 AM, Room T5, Boston Convention Center
Presenter: Madison May, Machine Learning Architect and Co-founder, Indico

Transfer learning, the practice of applying knowledge gained on one machine learning task to aid the solution of another, has seen historic success in the field of computer vision. Output representations of generic image classification models trained on ImageNet have been leveraged to build models that detect the presence of custom objects in natural images. Classification tasks that might require hundreds of thousands of images can be tackled with mere dozens of training examples per class thanks to these pre-trained representations.

The field of NLP, however, has seen more modest gains from transfer learning, with most approaches limited to the use of pre-trained word representations. This session will explore parameter and data-efficient mechanisms for transfer learning on text and show practical improvements on real-world tasks. We’ll also demo Enso, a newly open-sourced library designed to simplify benchmarking of transfer learning methods on a variety of target tasks. Attendees will learn about:

  • How Transfer Learning can deliver efficiencies in machine learning on text-based content.
  • Simplifying machine learning benchmarking with Enso.
  • Tools in Enso that enable the fair comparison of varied feature representations and target task models as the amount of training data is incrementally increased.

About Indico
Indico is an enterprise AI solution for unstructured content. Our focus is on helping to automate tedious back-office tasks, improving the efficiency of labor-intensive document-based workflows, and extracting valuable insights from unstructured content, including text and images. Our breakthrough in solving these challenges is an approach known as transfer learning, which allows us to train machine learning models with orders of magnitude less data than required by traditional content analysis techniques. With Indico, enterprises are now able to benefit from the dramatic advantages of machine learning at a fraction of the time. For more information, visit. https://indico.io/.



            

Coordonnées