Machine Learning Times
Machine Learning Times
EXCLUSIVE HIGHLIGHTS
Effective Machine Learning Needs Leadership — Not AI Hype
 Originally published in BigThink, Feb 12, 2024.  Excerpted from The...
Today’s AI Won’t Radically Transform Society, But It’s Already Reshaping Business
 Originally published in Fast Company, Jan 5, 2024. Eric...
Calculating Customer Potential with Share of Wallet
 No question about it: We, as consumers have our...
A University Curriculum Supplement to Teach a Business Framework for ML Deployment
    In 2023, as a visiting analytics professor...
SHARE THIS:

5 years ago
Wise Practitioner – Predictive Analytics Interview Series: Kunling Geng at Decision Engines Inc.

 

By: Luba Gloukhova, Founding Chair, Deep Learning World

In anticipation of his upcoming conference presentation at Deep Learning World Las Vegas, June 16-20, 2019, we asked Kunling Geng, Lead Data Scientist & AI Architect at Decision Engines Inc., a few questions about his work in deep learning. Catch a glimpse of his presentation, Deep Learning For Startup Companies — When You Only Have Little Data to Start With, and see what’s in store at the DLW conference in Las Vegas.

Q: In your work with deep learning, what do you model (i.e., what is the dependent variable, the behavior or outcome your models predict)?

A: The model tries to extract the structures’ information from a non-structure document (PDF, image files, etc), such as invoice date, purchase order number, tables, etc.

Q: How does deep learning deliver value at your organization – what is one specific way in which model outputs actively drive decisions or operations?

A:  We use deep learning models and AI technology to help human to reduce the redundant work by automating the daily repetitive work.

Q: Can you describe a quantitative result, such as the performance of your model or the ROI of the model deployment initiative?

A:  The model achieved more than 90% accuracy for processing invoices in the test data set.

Q: What surprising discovery or insight have you unearthed in your data?

A: Although we have entered the big data era, sometimes for a startup company like us, the data we can get is really limited due to the privacy and administrative concerns. Deep learning models usually require tons of data for training. Therefore, we have to come up with a smart way to deal with this challenge.

Q: What excites you most about the field of deep learning today?

A: The deep learning models make the impossible possible now. It can help human to reduce the redundant work by automating the daily repetitive work. Therefore, AI technologies will create the next Industrial Revolution.

Q: Sneak preview: Please tell us a take-away that you will provide during your talk at Deep Learning World.

A: The talk presents a new strategy for training deep learning models — “Lean Deep Learning”. Just similar to “Lean Startup” concept, “Lean Deep Learning” offers a practical approach of training deep learning models very limited data and resources.

—————————–

Don’t miss Kunling’s presentation, Deep Learning For Startup Companies — When You Only Have Little Data to Start With, at DLW on Wednesday, June 19, 2019 from 4:20 to 4:40 PM. Click here to register for attendance.

By: Luba Gloukhova, Founding Chair, Deep Learning World

This content is restricted to site members. If you are an existing user, please log in on the right (desktop) or below (mobile). If not, register today and gain free access to original content and industry news. See the details here.

Comments are closed.