What is the difference between supervised and unsupervised learning?
Neural nets like human neurons can learn to recognise any pattern.
Inputs put into a device initiate particular patterns which in turn
lead to an output. The net is guided to acknowledge a pattern by
feedback (behaviourism). Everytime an output is correct, its
original pattern is back propagated past each connection and
strengthened. Once one unit is activated it is likely to be
activated over and over (Hebb's rule). Whereas if a wrong output is
the case, those 'input to output' connections are weakened.
Eventually, this trial and error method succeeds to produce the right
output more and more frequently. Learning has been supervised to
improve results each try. Whereas, unsupervised learning receives no
feedback on an outcome. The consequences of it have no significance.
Learning has to rely on the existing physical structure of the
pattern to categorise features to certain outputs.
'Nettalk' (Rosenberg and Seynowski, 1987) is an artificial example of
supervised learning where the pronounciation of letters is the
output. Everytime the right letter is produced, feedback strengthens
that connection or weakens it for a wrong letter. This supervised
learning technique has an 80% success rate for pronouncing correct
words. Feedback is also available in real life; getting sunstroke
from too much sun teaches most people to moderate exposure for
example. Supervised learning of any pattern succeeds due to the
guidance of feedback in nets with many layers. However the exclusive
OR pattern (same output from different inputs) is unlearnable in
basic two layer nets. Supervision aids quick results whereas
unsupervised learning takes an inefficient approach.
This archive was generated by hypermail 2b30 : Tue Feb 13 2001 - 16:23:42 GMT