Bias variable names are a little confusing

The bias nodes exist only in pre-output layers, but for example, the weight connected the the hidden bias neuron is called `bias_o`. This confused me a lot, so I think it is easier to understand `bias_o` as `bias_h` and `bias_h` as `bias_i`. This way I think it's easier to read the code that updates the biases, since the gradient from the output layer, for example, is mapped to the bias in the *previous* layer, as the process of backpropagation might suggest by its name.

Search the repository for `bias_o` and `bias_h`, then inspect the bias-update code and surrounding variable definitions. Rename the variables consistently so the output-connected bias uses `bias_h` and the hidden-connected bias uses `bias_i`, while preserving the existing updates.

Vom Indexierungsmodell aus dem Issue-Text verfasst.