View Single Post
  #19   Spotlight this post!  
Unread 04-21-2015, 10:00 PM
Ben Wolsieffer Ben Wolsieffer is offline
Dartmouth 2020
AKA: lopsided98
FRC #2084 (Robots by the C)
Team Role: Alumni
 
Join Date: Jan 2011
Rookie Year: 2011
Location: Manchester, MA (Hanover, NH)
Posts: 520
Ben Wolsieffer has much to be proud ofBen Wolsieffer has much to be proud ofBen Wolsieffer has much to be proud ofBen Wolsieffer has much to be proud ofBen Wolsieffer has much to be proud ofBen Wolsieffer has much to be proud ofBen Wolsieffer has much to be proud ofBen Wolsieffer has much to be proud of
Re: Tired of tuning pesty PID loops for hours? Try Neural Networks!

I found something which greatly improves the performance of the learning process. In neuron.cpp, you calculate the derivative of the transfer function at output value, when I am pretty sure it should be calculated using the sum of the inputs. Before I made that change, both your C++ version and my Java version would only find a good solution to xordata.txt maybe 10% of the time. I'm not sure if you had more success. It now works nearly 100% of the time after making that change. Also, I think you meant to call "transferFunctionTanHDerivative" instead of "transferFunctionTanH" on line 129 of neuron.cpp.

On an unrelated note, you should probably include a .gitignore file in your repository so you don't accidentally commit backup and binary files.
__________________



2016 North Shore District - Semifinalists and Excellence in Engineering Award
2015 Northeastern University District - Semifinalists and Creativity Award
2014 Granite State District - Semifinalists and Innovation in Control Award
2012 Boston Regional - Finalists
Reply With Quote