• Dr. B.Sarojamma
• K.Geetha
• Dr. S.Venkatramana Reddy.

Implementation of Activation Functions in Elman Back propagation Neural Network, NARX(Non-linear Auto Regressive Exogeneous) and Feed Forward Back Propagation Neural Network have been done and also studied the effects of those Activation Functions in terms of Accuracy by using the best measure known as RMSE. We have discussed Best Validation Performance in all the cases. We used very large dataset, which is for a period of five years of our country consisting of Weather parameters such as Minimum Temperature, Maximum Temperature, Visibility and Wind speed for Training, Testing and Validation. In the present work Elman Back Propagation shows accurate results. Simultaneously, Activation Function TANSIG supports the Neural network with not much difference comparing to others.

Back Propagation Neural Network, NARX, Feed Forward Neural Network, Activation Function, NN Tool.

"Effects and Analysis of Activation Functions in Artificial Neural Networks Using NN Tool In Matlab on Weather Parameters.", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.8, Issue 9, page no.a609-a612, September-2021, Available :http://www.jetir.org/papers/JETIR2109088.pdf

"Effects and Analysis of Activation Functions in Artificial Neural Networks Using NN Tool In Matlab on Weather Parameters.", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.8, Issue 9, page no. ppa609-a612, September-2021, Available at : http://www.jetir.org/papers/JETIR2109088.pdf