See

https://svn-d1.mpi-inf.mpg.de/AG1/MultiCoreLab/papers/ebook-fuzzy-mitchell-99.pdf

http://www2.cs.uh.edu/~ceick/6367/eiben3.pptx

http://www2.cs.uh.edu/~ceick/6367/eiben1.pptx

http://www2.cs.uh.edu/~ceick/6367/eiben2.pptx

http://www2.cs.uh.edu/~ceick/6367/eiben4.pptx

Following are the new and promising metaheuristic algorithms:

1- Bacterial Foraging Algorithm

2- Fireworks Algorithm

3- Brain Storm Optimization Algorithm

4- Bat Algorithm

5- Firefly Algorithm

it is not clear, you should evalute different methods in order to find the better algorithm

Hi Marko Tscherepanow,

Thank u so much for your recommendation, your  thesis information was interesting to me. I must read it with more details.

And also, Is that possible to send me more papers between 2015 to 2017 about recurrent neural networks ?

Hi Loopinder Sood,

Thank you for promising algorithms, I did not read about  Bacterial Foraging Algorithm, Fireworks Algorithm and Brain Storm Optimization Algorithm. 

This are quiet helpful for my research.

Hi Ali Asghar Heidari ,

Yes,absolutely  right, but i just ask to see if anyone did this before or not.

Thank you Jung-Hun Jeonghoon Yang ryang.

I am glad this question was helpful.

Thanks dear Marko, this book is very usefull for my research.

Till now what I have experienced that second order method such as Scaled conjugate gradient methods provide better convergence and it is faster too. How ever if you are thinking for a evolutionary method you can try with differential evolution and bio geography based optimization. Hope it will work better in smaller size ANN.

Gradient Evolution, Triangular DE are some evolutionary algorithms, and used for optimize parameters of NN like initial weights and bias. Some application of artificial intelligence used this algorithm like Uncertain system control, Nonlinear system approximation, Time series analysis, Prediction and Forecasting etc. Please see the following link:

http://www.worldscientific.com/doi/abs/10.1142/S1469026816500164

http://link.springer.com/article/10.1007%2Fs40815-016-0145-5

Hi Dear Uday,

Thank you very much for your update recommendation paper, It will help for my point of view and applications. 

Dear Fatemeh Bandi,

the phrase " evolutionary algorithms " is limited.It is better to utilize "Meta-heuristic algorithms". By this consideration, I think PSO (especially APSO) is one of the high speed algorithms for this category.

you should remember, the convergence speed is not the only problem. for instance, trapping in the local minimum is a usual disadvantages of this algorithm. 

in addition, if you want newer algorithms, I suggest the links below:

1) World cup optimization

2) Quantum invasive weed optimization algorithm

http://link.springer.com/article/10.1007/s40313-016-0242-6

Article An Improved Quantum Evolutionary Algorithm Based on Invasive...

Hi dear Navid,

Thank you for useful comment and recommend papers.

Just one question,for solution of trapping in local minimum is it better to used hybrid algorithms or multi-modal ? or do you have any better idea?

From my experiences, I think using hybrid methods made good results. 

For using hybrid method, try to hybrid two methods which one of them has a high performance in Exploration and the other in Exploitation. If you select two proper algorithms, it will be have good results.

For example, PSO has high speed and made good results for Exploitation, while:

GA has a high accuracy in Exploration; Since good hybridizing these two algorithms can made good results. 

Of course, I suggest you to utilize new algorithms. GA-PSO is almost an old method.

Dear Navid,

Thank you  for your Useful explanation.

I will research for new methods of hybridizing.

Dear Amir,

Sure, cuckoo search algorithm has many parameters for convergence control, but too many parameters does not mean that complexity of the algorithm is  getting high ?