The results of my training in Matlab and artificial intelligence are far from each other. What should I do?

2 views (last 30 days)
mert2=newff(inpdata,autdata(2,:)/1.6,20);
mert2.trainFcn='traingdx'
mert2.trainParam.max_fail=100;
mert2.trainParam.lr=0.000001;
mert2.trainParam.mu=0.5;
%mert2.trainParam.epochs=5000;
mert2=train(mert2,inpdata,autdata(2,:)/1.6);
nresult2=1.6*sim(mert2,inpdata );
180*nresult2 /pi

Answers (1)

Shashank Gupta
Shashank Gupta on 25 May 2021
Hi Mert,
The function newff is obsoleted. In order to create a feedforward network, you can use some other function like feedforwardnet or fitnet. In either case, you need to design an optimized neural network for your data to get the best performance. Try looking at the existing examples in the documentation of this function and start designing your network. There is no hard and fast rule here to get the optimized results. You have to understand your data, visualize it and then design your network based on the data.
I hope this helps.
Cheers

Categories

Find more on Deep Learning Toolbox in Help Center and File Exchange

Products


Release

R2020b

Community Treasure Hunt

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

Start Hunting!