6.034 Artificial Intelligence - Recitations, fall 2004 online slides on learning |
|
|
Next: Function Learned By One Layer Net Previous: Example
The AND Function
w1 = 2, w2 = 1, threshold = 2
x2
+ = Class 1 - | +
- = Class 2- *|
- - |+
* + +
- - - | + + +
------------|*----------- x1
- - | +
- -| * + +
- - - - | + +
- -| *
|
2x1 + x2 = 2
Notice that the classes can be separated by a line (hyperplane )
Learn XOR of two inputs, x1 and x2.
Why does one layer net run forever and never converge?
