The Periodic Table of AI

The Periodic Table of AI

*This content is best viewed on desktop.

This is an invitation to collaborate.  In particular, it is an invitation to collaborate in framing how we look at and develop machine intelligence. Even more specifically, it is an invitation to collaborate in the construction of a Periodic Table of AI.

Let’s be honest. Thinking about Artificial Intelligence has proven to be difficult for us.  We argue constantly about what is and is not AI.  We certainly cannot agree on how to test for it.  We have difficultly deciding what technologies should be included within it.  And we struggle with how to evaluate it.

Even so, we are looking at a future in which intelligent technologies are becoming commonplace.  Take personal assistants, albeit simple, they are now on our phones and in our homes.  Intelligent analytical systems are beginning to evaluate our credit worthiness, investment risks and massive transactional flows to alert us about fraud and money manipulation. And even ignoring the possibilities associated with having our health tracked and maintained by agents with access to every piece of online medical information, we are surrounded by systems that track our transactions, interests and connections in order to give us advice about who we might want to be friends with, what we might want to buy and even who we should consider dating.

Click to view descriptions.

Note: Periodic Table is best viewed on desktop.

In order to better understand the systems we are building, we need to figure out a better way to talk about them.

With that in mind, we propose an approach to viewing machine intelligence from the perspective of its functional components. Rather than argue about the technologies behind them, the focus should be on the functional elements that make up intelligence.  By stepping away from how these elements are implemented, we can talk about what they are and their roles within larger systems.

Our goal is to build a simple framework for the conversations we need to have as we build the future. In particular, we want a framework to help us make sure that as we build, evaluate and compare different systems, we can understand and articulate what it is they are supposed to be doing.

In order to avoid imposing any architecture on these components, we have structured this exploration around individual elements that can be pulled together in different ways depending on the need, thus a Periodic Table of AI.

Of course, this table is the start, not the end. Our hope is that over time, the elements will be refined and expanded upon and the table itself reorganized. Our goal is to encourage this collaboration and start the conversation we need to have as we use these elements to build the future of artificial intelligence.

Read the full article here.


As Chief Scientist and co-founder, Kris focuses on R&D at Narrative Science. His main priority is to define the future of Advanced NLG, the democratization of data-rich information and how language will drive both interactive communications and access to the Internet of Things (IoT). In addition to being Chief Scientist, Kris is a professor of Computer Science at Northwestern University.

Related News

Share this page

Become a Part of the Future! Sign Up for Our Newsletter: