Memory management for unrolled graphs

[emjotde]

Graphs that are unrolled for different batch size when they contain RNNs should share the entire memory in order to avoid allocation. Parameters should be protected, the rest could be overwritten.

It probably makes sense to change the Tensor class to not hold it's own memory, rather it should be a view on a segment of the memory the graph holds. This should be solved together with issue #9 .