> what kind of neural-net architecture and training would allow a model to handle numbers lengths it hasn't been trained on
A recurrent neural network implementing binary addition with carry could do this, and one can derive the correct weights with pen and paper without too much effort.
Whether gradient descent will find them too is another matter entirely
A recurrent neural network implementing binary addition with carry could do this, and one can derive the correct weights with pen and paper without too much effort.
Whether gradient descent will find them too is another matter entirely