Mar 15–18, 2020

Using deep learning to understand documents

Eitan Anzenberg (
1:45pm2:25pm Tuesday, March 17, 2020
Location: Expo Hall

Who is this presentation for?

Data scientists or analysts




Extracting key fields from a variety of document types remains a challenging machine learning problem. Services such as AWS and Google Cloud provide text extraction products to “digitize” images or PDFs. These return phrases, words, and characters with their corresponding coordinate locations. Working with these outputs remains challenging and unscalable as different document types require different heuristics with new types uploaded daily. Furthermore, a performance ceiling is reached when algorithms work perfectly, equaling the accuracy of the service OCR.

Eitan Anzenberg proposes an end-to-end scalable solution using deep learning and OCR architecture to automatically extract important text fields from documents. Computer vision algorithms using deep learning produce state-of-the-art classification accuracy and generalizability through training on millions of images. Region proposals are generate by off-the-shelf OCRs, including Tesseract. He compares in-house model accuracy with third-party OCR services. is working to build a paperless future. It parses through 60M documents a year, ranging from invoices, contracts, receipts, and a variety of other types. Understanding those documents is critical to building intelligent products for its users.

Prerequisite knowledge

  • A basic understanding of deep learning computer vision algorithms
  • Familiarity with machine learning

What you'll learn

  • Learn how to experiment with deep learning architectures and how to deploy deep learning models to production
  • Identify requirements for training deep learning models
Photo of Eitan Anzenberg

Eitan Anzenberg

Eitan Anzenberg is the director of data science at and has many years of experience as a scientist and researcher. His recent focus is in machine learning, deep learning, applied statistics, and engineering. Previously, Eitan was a postdoctoral scholar at Lawrence Berkeley National Lab, received his PhD in physics from Boston University, and his BS in astrophysics from University of California, Santa Cruz. Eitan has 2 patents and 11 publications to date and has spoken about data at various conferences around the world.

Leave a Comment or Question

Help us make this conference the best it can be for you. Have questions you'd like this speaker to address? Suggestions for issues that deserve extra attention? Feedback that you'd like to share with the speaker and other attendees?

Join the conversation here (requires login)

Contact us

For conference registration information and customer service

For more information on community discounts and trade opportunities with O’Reilly conferences

Become a sponsor

For information on exhibiting or sponsoring a conference

For media/analyst press inquires