Thomas Wagenaar

Well i'm doing the exact same thing at the moment with genetic algorithms, so we are talking about performing the crossover operation on two networks? It's easier to merge two...

I am creating an extension of synaptic having built in functions like this. Take a look [here](https://github.com/wagenaartje/gynaptic)

If you input words, you have to convert them (one-hot encoding probably). Maybe [this](https://wagenaartje.github.io/neataptic/docs/tutorials/normalization/) and [this](https://github.com/cazala/synaptic/wiki/Normalization-101) will help you out. You can't prevent negative weights, and don't try, because they...

I've been trying to make a solution to this problem, but I also can't seem to figure out what you can do with a LayerConnection of two networks. For some...

Where is this link located? Wiki is just located on [Github Wiki](https://github.com/cazala/synaptic/wiki)

@Jabher @cazala why is another cost function necessary? I went through synaptic code and the cost function in no way effects the backpropagation algorithm. In synaptic, the cost function is...

Ehm, what have you tried? Examples on the README.md show examples of a dataset. Each sample in a data set can have basically unlimited length (input and output). Input and...

GPU.js seems pretty awesome, but it's not always faster: https://jsfiddle.net/zkL3av3o/1/ (change `matrixSize` to your needs). The benchmark also runs without taking the time to initialise a kernel into account. So...

For testing the current error, use `myTrainer.test(dataSet, options)` after you have created a trainer. [See the wiki for more info](https://github.com/cazala/synaptic/wiki/Trainer#test)

I think this is because you are running the JavaScript in `strict` mode. Try running it in non-strict mode to see if it still throws an error. It's weird, because...