General code of back propagation feed forward neural network

6 views (last 30 days)
Hi, I am looking for a general matlab code for BPFFNN I have 4 inputs and output is either 0 or 1. I need a general code which I can modify as per my requirement. Thank You

Answers (1)

Greg Heath
Greg Heath on 6 Jun 2017
Edited: Greg Heath on 6 Jun 2017
HAH!!! Trying to use one code for everything is a fool's errand. That is why MATLAB offers several generic codes for several generic categories. Use the help and doc commands to see the documentation and examples for each category:
1. FITNET - Regression and Curve-Fitting
2. PATTERNNET - Classification and Pattern-Recognition
3. TIME SERIES
3a. TIMEDELAYNET - Time-Series with inputs consisting of either
i) Current and delayed applied external signals
or
ii) Only delayed applied external signals
3b. NARNET - Time-series with inputs consisting of ONLY delayed
output feedback signals
3c. NARXNET - Time-series with inputs consisting of delayed
output feedback signals AND EITHER OR BOTH
i. Current applied inputs
ii. Delayed applied inputs
4. NOTE:
a) Timedelaynet and Narnet are SPECIAL CASES of Narxnet
b) Causality requires that all output feedback signals must be
delayed from the time of the input which caused it.
Consequently, it is sufficient to be familiar with only FITNET, PATTERNNET and all variations of NARXNET.
Hope this helps.
Thank you for formally accepting my answer
Greg
  1 Comment
Greg Heath
Greg Heath on 6 Jun 2017
Edited: Greg Heath on 6 Jun 2017
In addition to the data used in the help and doc documentation, additional MATLAB data can be obtained using the following commands
help nndatasets
doc nndatasets
Therefore if you have questions to post, it would be very smart to use one or more of the MATLAB datasets as examples.
In addition, it would be wise to first search both the NEWSGROUP and ANSWERS before posting a question. For example, if you have a classification/pattern-recognition problem, a reasonable search might start with
greg patternnet
Hope this helps.
Greg

Sign in to comment.

Categories

Find more on Sequence and Numeric Feature Data Workflows in Help Center and File Exchange

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!