AI Lab4: Neural Networks
Due Monday May 5th at midnight. Paper due under my door by Wednesday May 7th at noon.
Program:
Build a simple three layer Neural Neural network that learns through back-propagation.
consider the following inputs and target outputs:
MO:
1 1 0
0 1 1
1 0 1
1 0
NM: 1 0 0 0 1 1 1 1 1 1 0
MN: 0 0 0 0 0 0 0 0 1 0 0
OH:
1 1 0
0 1 1
1 0 1 1 0
FL: 1 1 0 1 1 1 1 0 1 1 0
VA:
1 1 1
1 1 1
1 1 1 1 0
PA:
0 0 0
0 1 1
1 0 1
0 0
NH: 0 1 0 0 1 1 1 1 1 1 0
OUT: 1 1 0 0 1 1 1 0 1 1 0
Make
your network have no more than 4 hidden layers. First train the network
on the first 4 sets of input and output. When you are satisfied that
your network has learned this limited training data, test it on the
next four examples. How did it do? Explain that in your papger. Now
have it learn from scratch using all but the first example. (throw away
your earlier weights). Once the network is fully trained, test it on
the first (leftmost) example above. How did your network do? Mention
its performance and discuss in your paper.
Paper:
Write a
paper discussing the merits of neural networks using Backpropagation as
a learning technique. As usual include an analys of how intelligent the
technique appears to be, how flexible and the rest.
paper
outline. Have at least this in your paper. You are encouraged to cover
more if you find something interesting about your program or you have
some other insite into the technique
Introduction: What is this technique and what class of problems does it solve
Discussion
of the technique. Where is the intelligence? How much intelligence is
there. What sorts of applications would you use this technique for
Discussion of your implementation: What interesting things did you see in your own implimentation of neural nets
Summary: what classes of problems should this technique solve and in your experience, what would they solve?