Put AI to work
June 26-27, 2017: Training
June 27-29, 2017: Tutorials & Conference
New York, NY

Tackling the limits of deep learning

Richard Socher (Salesforce)
11:05am11:45am Wednesday, June 28, 2017
Implementing AI
Location: Grand Ballroom West
Secondary topics:  Deep Learning
Average rating: ****.
(4.60, 5 ratings)

What you'll learn

  • Explore solutions to the problems and limitations of deep learning


Deep learning has made great progress in a variety of language tasks. However, there are still many practical and theoretical problems and limitations. Richard Socher shares some solutions.

Topics include:

  • How to predict previously unseen words at test time
  • How to have a single input and output encoding for words
  • How to grow a single model for many tasks
  • How to use a single end-to-end trainable architecture for question answering
Photo of Richard Socher

Richard Socher


Richard Socher is chief scientist at Salesforce, where he leads the company’s research efforts and works on bringing state-of-the-art artificial intelligence solutions to Salesforce. Previously, Richard was the CEO and founder of MetaMind (acquired by Salesforce in April 2016). MetaMind’s deep learning AI platform analyzes, labels, and makes predictions on image and text data so businesses can make smarter, faster, and more accurate decisions than ever before. He was awarded the Distinguished Application Paper Award at the International Conference on Machine Learning (ICML) 2011, the 2011 Yahoo Key Scientific Challenges Award, a Microsoft Research PhD fellowship, a “Magic Grant” from the Brown Institute for Media Innovation, and the 2014 GigaOM Structure Award. Richard holds a PhD in deep learning from Stanford, where he worked with Chris Manning and Andrew Ng. His research won the Best Stanford CS PhD Thesis award.