Symbolic AI in a Machine Learning Age

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.

 
1 favorite thumb_down thumb_up 2 comments visibility_off  Remove from Watchlist visibility  Add to Watchlist
 

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 2 months ago

Public Feedback

comment Suggest improvements to the Speaker
  • Naresh Jain
    By Naresh Jain  ~  1 month ago
    reply Reply

    Thanks, Anne for the proposal. Do you think 20 mins would be sufficient for this talk+demo? Or you want to expand it to 45 mins?

    • Anne Ogborn
      By Anne Ogborn  ~  1 month ago
      reply Reply

      On rereading the proposal, I think you're right.

      OK, 45 it is