Imran's personal blog

May 26, 2016

Genetic Algorithms vs Gradient Descent

Filed under: Uncategorized — ipeerbhai @ 8:28 pm

I’ve been working with a BitArray pattern recognition system for sound processing.  I implemented a genetic algorithm with a single-point mutation ability and tested that algorithm against a data set of sounds ( me talking and a recording of violins playing.  The idea is to detect me talking over the violin noise, with the hope of eventually being able to tell speech from noise apart. )

It didn’t work at all.  I could create semi-optimal ( aka local minima ) solutions that could mostly guess me talking vs the violin, but not always.  There was a global solution — by pure chance I hit it a few times where the system worked correctly. ( about 1/10 of the time, I hit the correct global optima, 9/10 I hit a local optima ).

I wanted to see if I could evolve the local optima detectors to the global.  With a SNIP mutation, it didn’t work ( though I hypothesized it should work some of the time.  The global optima is a single bit, bit 47, being false in the encoded samples. )

I calculated from this the number of mutations to get to global optima from all suboptimal solutions.  I calculate at least 4 to around 7 serial snips, with add/deletion being far more valuable than transpose.

Cost tracking indicates that the global optima takes 318,000 if/then tests to achieve in a good case.  ( 500 sample points in the space — small data… )

I have no idea what gradient descent would take here.  But, I now know an appropriate DNN topography to guess correctly.   25 samples in input layer, 25 neurons + bias, and 1 output neuron should simulate my genetic selector.  Then I can tell what is more efficient.  I’m suspecting that poly-snip genetic would work, along with 25 neuron DNN.  I’ll have to impliment both and see which is more efficient DNN or Genetic?

Leave a Comment »

No comments yet.

RSS feed for comments on this post. TrackBack URI

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

Blog at

%d bloggers like this: