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.

Busca en el repositorio `bias_o` y `bias_h`, y luego inspecciona el código de actualización de los biases y las definiciones de las variables circundantes. Cambia el nombre de las variables de forma coherente para que el bias conectado a la salida use `bias_h` y el bias conectado a la capa hidden use `bias_i`, conservando las actualizaciones existentes.

Escrito por el modelo de indexación a partir del texto del issue.