Demonstrations

From 6.034 Wiki

(Difference between revisions)
Jump to: navigation, search
Line 14: Line 14:
* Learning: nearest neighbors, support vector machines, lattice learning, boosting
* Learning: nearest neighbors, support vector machines, lattice learning, boosting
* Neural nets: autocoding, logistic regression
* Neural nets: autocoding, logistic regression
-
<!--
+
 
'''The demonstration software is unavailable temporarily pending renewal of a certificate.
'''The demonstration software is unavailable temporarily pending renewal of a certificate.
'''
'''
-
-->
+
 
 +
<!--
If you don't have the Java 8 Runtime Environment installed,  
If you don't have the Java 8 Runtime Environment installed,  
Line 27: Line 28:
Then, you
Then, you
can run the [https://courses.csail.mit.edu/6.034f/demonstrations/demonstrations.jnlp latest version].
can run the [https://courses.csail.mit.edu/6.034f/demonstrations/demonstrations.jnlp latest version].
 +
 +
-->

Revision as of 15:54, 13 October 2018

Much of the material in 6.034 is reinforced by on-line artificial-intelligence demonstrations develop by us or otherwise available on the web. Those demonstrations developed by us are provided via the easy-to-use Java Web Start mechanism, which comes with the Java Runtime Environment, the so-called JRE.

The demonstrations illustrate the following ideas:

  • Blocks world manipulation (after Winograd)
  • Search: depth-first, breadth-first, hill-climbing, beam, branch and bound, A*
  • Games: mini-max, alpha-beta
  • Genetic algorithms: crossover, mutation, fitness
  • Constraint satisfaction: drawing analysis (after Waltz, using Huffman labels)
  • Domain reduction: map coloring, resource allocation
  • Biological mimetics: genetic algorithms, self-organizing maps, cross-modal clustering
  • Learning: nearest neighbors, support vector machines, lattice learning, boosting
  • Neural nets: autocoding, logistic regression

The demonstration software is unavailable temporarily pending renewal of a certificate.


Personal tools