Lewis Van Winkle

Are you offering to help?

You can set `activation_hidden` and `activation_output`. However, a linear activation function is not able to solve a non-linear problem, such as xor used in the examples.

Yes, back-propagation is only implemented for sigmoid. Other training methods can still work with other activation functions. If back-prop is needed, it'll need to be implemented.

@msrdinesh Sure. Give it a go. Just please keep it short and simple. I think you can mirror the way that output and hidden activation functions are used.

>Was this done on purpose to show some kind of limitation of back propagation ? No. It's randomized, so it takes more loops sometimes. I'll increase it.

Actually, it's possible you got stuck in a local minima. If you change it back to 300 iterations, and run the program several times, how often does it work?

Ok, thanks for the feedback. I'll look into it and tune things a bit when I have some free time.

Hi Gavin, No, I haven't done it like that using only one socket before. What I have done, is opened a separate socket on each interface, and then the receiving...

Hi Ajay, It looks like this code is used in both `time_server_dual.c` and `server_reuse.c`. The error you are describing would only happen if you are compiling the code as C++....

That is very true. I tried very hard to make all of the code C and C++ valid. I just missed this case. I will try to update the code...