0% found this document useful (0 votes)
350 views11 pages

Symbolic vs. Subsymbolic

The document discusses symbolic and subsymbolic approaches in artificial intelligence. Symbolic AI uses rules, logic, and symbol manipulation while subsymbolic AI relies on machine learning techniques like neural networks. Over time, the approaches have incorporated aspects of each other, with symbolic AI using statistical methods and subsymbolic AI employing symbolic concepts. The goal of both is to develop intelligent computer systems that can perform tasks considered intelligent if performed by humans.

Uploaded by

muhammadriz
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
350 views11 pages

Symbolic vs. Subsymbolic

The document discusses symbolic and subsymbolic approaches in artificial intelligence. Symbolic AI uses rules, logic, and symbol manipulation while subsymbolic AI relies on machine learning techniques like neural networks. Over time, the approaches have incorporated aspects of each other, with symbolic AI using statistical methods and subsymbolic AI employing symbolic concepts. The goal of both is to develop intelligent computer systems that can perform tasks considered intelligent if performed by humans.

Uploaded by

muhammadriz
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 11

Symbolic vs.

Subsymbolic AI

Henry Lieberman
MIT CSAIL & MIT Media Lab

Henry Lieberman • MIT


Symbolic vs. Subsymbolic

Explicit symbolic Bayesian learning


programming
Deep learning
Inference, search
algorithms Connectionism

AI programming Neural Nets / Backprop


languages LDA, SVM, HMM, PMF,
Rules, Ontologies, alphabet soup…
Plans, Goals…

Henry Lieberman • MIT


Symbolic vs. Subsymbolic

Introspection more useful More robust against noise


for coding
Better performance
Easier to debug
Less knowledge upfront
Easier to explain
Easier to scale up
Easier to control
Big Data
Not so Big Data
More useful for connecting to
More useful for explaining neuroscience
people’s thought
Better for perceptual
Better for abstract problems
problems

Henry Lieberman • MIT


What’s the goal of AI?

To have computers do things, that, if people did


them, we would consider intelligent
(subject to “Disappearing AI”)
To explain how human intelligence works, and
reproduce it in computers

Henry Lieberman • MIT


What is the appropriate level for
describing intelligence?

We’re just bags of chemicals…. Can we explain


intelligence in terms of chemistry?
We’re just a bunch of connected neurons…. Can we
explain intelligence in terms of wiring?
We’re just information processors… Can we explain
intelligence in terms of information?
We’re just {math, bio, genetic, social, …}

Henry Lieberman • MIT


Symbolic vs Subsymbolic

Henry Lieberman • MIT


Newell & Simon:
The Physical Symbol System
Hypothesis

Henry Lieberman • MIT


Timeline

Subsymbolic

Symbolic
__________________________________________________
1940 1950 1960 1970 1980 1990 2000 2010

Henry Lieberman • MIT


Reconciling approaches

Top down vs. bottom up


Bits of the other approach are seeping into both
sides

Henry Lieberman • MIT


Peace!

Henry Lieberman • MIT


Henry Lieberman • MIT

You might also like