Before machine learning took over, AI was done symbolically.

Symbolic methods still have value, and merging of symbolic and statistical methods is an emerging research area.

In particular, symbolic methods often have much greater explanatory power. Fusing symbolic methods with ML often creates a more explicable system.

In this talk we will explore some areas of active work on hybrid applications of symbolic and machine learning.


Outline/Structure of the Talk

Quick review of symbolic methods.

Present some commercial users of hybrid methods (Kyndi, Simularity).

Show a bit of cplint.

Demonstrate a statistical solution to JUDGE.

Learning Outcome

Participants will come away with 'root pointers' to various technologies and techniques that can lead to integrating symbolic AI into modern ML practice.

Target Audience

ML folks who are looking for explanatory power

Prerequisites for Attendees

An open and curious mind.

Knowledge of fundamentals of ML would be helpful.

Knowledge of Prolog on the family tree level would be helpful, but not necessary.


schedule Submitted 3 years ago