Popular recipes tagged "neural" but not "genetic_algorithm" and "artificial_intelligence"http://code.activestate.com/recipes/tags/neural-genetic_algorithm-artificial_intelligence/popular/2014-09-11T06:25:14-07:00ActiveState Code RecipesTeach your computer a few tricks (Python)
2014-09-11T06:25:14-07:00Alexander Pletzerhttp://code.activestate.com/recipes/users/4190754/http://code.activestate.com/recipes/578932-teach-your-computer-a-few-tricks/
<p style="color: grey">
Python
recipe 578932
by <a href="/recipes/users/4190754/">Alexander Pletzer</a>
(<a href="/recipes/tags/anl/">anl</a>, <a href="/recipes/tags/back/">back</a>, <a href="/recipes/tags/network/">network</a>, <a href="/recipes/tags/neural/">neural</a>, <a href="/recipes/tags/propagation/">propagation</a>).
</p>
<p>Following is an artifical neural network program that takes any number of inputs and any number of hidden layers, and spits out an output. It applies back propagation with regularization to minimize the cost function. A gradient descent algorithm tries to find the minimum of the cost function in the landscape of weights. </p>
Simple Back-propagation Neural Network in Python source code (Python)
2012-05-30T17:09:49-07:00David Adlerhttp://code.activestate.com/recipes/users/4182015/http://code.activestate.com/recipes/578148-simple-back-propagation-neural-network-in-python-s/
<p style="color: grey">
Python
recipe 578148
by <a href="/recipes/users/4182015/">David Adler</a>
(<a href="/recipes/tags/back/">back</a>, <a href="/recipes/tags/back_propagation/">back_propagation</a>, <a href="/recipes/tags/neural/">neural</a>, <a href="/recipes/tags/neural_network/">neural_network</a>, <a href="/recipes/tags/propagation/">propagation</a>, <a href="/recipes/tags/python/">python</a>).
</p>
<p>This is a slightly different version of this <a href="http://arctrix.com/nas/python/bpnn.py" rel="nofollow">http://arctrix.com/nas/python/bpnn.py</a></p>
Genetic Algorithm in Python source code - AI-Junkie tutorial (Python)
2012-06-19T12:59:13-07:00David Adlerhttp://code.activestate.com/recipes/users/4182015/http://code.activestate.com/recipes/578128-genetic-algorithm-in-python-source-code-ai-junkie-/
<p style="color: grey">
Python
recipe 578128
by <a href="/recipes/users/4182015/">David Adler</a>
(<a href="/recipes/tags/algorithm/">algorithm</a>, <a href="/recipes/tags/artificial/">artificial</a>, <a href="/recipes/tags/genetic/">genetic</a>, <a href="/recipes/tags/network/">network</a>, <a href="/recipes/tags/neural/">neural</a>, <a href="/recipes/tags/python/">python</a>).
Revision 5.
</p>
<p>A simple genetic algorithm program. I followed this tutorial to make the program <a href="http://www.ai-junkie.com/ga/intro/gat1.html." rel="nofollow">http://www.ai-junkie.com/ga/intro/gat1.html.</a></p>
<p>The objective of the code is to evolve a mathematical expression which calculates a user-defined target integer.</p>
<hr />
<p>KEY:</p>
<p>chromosome = binary list (this is translated/decoded into a protein in the format number --> operator --> number etc, any genes (chromosome is read in blocks of four) which do not conform to this are ignored.</p>
<p>protein = mathematical expression (this is evaluated from left to right in number + operator blocks of two)</p>
<p>output = output of protein (mathematical expression)</p>
<p>error = inverse of difference between output and target</p>
<p>fitness score = a fraction of sum of of total errors</p>
<hr />
<p>OTHER:</p>
<p>One-point crossover is used.</p>
<p>I have incorporated <strong>elitism</strong> in my code, which somewhat deviates from the tutorial but made my code more efficient (top ~7% of population are carried through to next generation)</p>