Sep 23–26, 2019

Data need not be a moat: Mixed Formal Learning enables zero and low shot learning

Sandra Carrico (Glynt.ai)
1:15pm1:55pm Thursday, September 26, 2019
Location: 1A 12/14
Secondary topics:  Text and Language processing and analysis

Who is this presentation for?

Experienced Data Scientists and Machine Learning Engineers and their managers

Level

Intermediate

Description

This will be a longer version of the talk I gave at IEEE ICSC 2019. The paper can be found: https://arxiv.org/abs/1901.06622

This talk will explain how companies with only small data sets can over come that limitation and develop state of the art machine learning solutions by modeling solutions with mathematical models.

Mixed Formal Learning, a new architecture that learns models based on formal mathematical representations of the domain of interest and exposes latent variables. The second element in the architecture learns a particular skill, typically by using traditional prediction or classification mechanisms. Our key findings include that this architecture: (1) Facilitates transparency by exposing key latent variables based on a learned mathematical model; (2) Enables Low Shot and Zero Shot training of machine learning without sacrificing accuracy or recall.

Prerequisite knowledge

How to turn daily problems into machine learning solutions and roughly how to implement those solutions.

What you'll learn

How to reframe their problems into partially mathematical solutions so that they can achieve state of the art performance with small data sets.
Photo of Sandra Carrico

Sandra Carrico

Glynt.ai

As Vice President of Engineering, Sandra leads WattzOn’s software development team, ensuring rapid iteration and releases using agile software development. Previously Sandra was VP of Engineering at a number of startups. She has also been in engineering management at AT&T Bell Labs, Aurigin and AT&T Labs.

As Chief Data Scientist, Sandra invented WattzOn’s GLYNT machine learning product, which extracts data trapped in complex documents. She is also the inventor of Mixed Formal Learning, which is used in the GLYNT machine learning product.

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

confreg@oreilly.com

For conference registration information and customer service

partners@oreilly.com

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

strataconf@oreilly.com

For information on exhibiting or sponsoring a conference

Contact list

View a complete list of Strata Data Conference contacts