Feature Request: Add Bitwise Operations for Tensors

[wcshds]

Bitwise operations are very common, and most deep learning frameworks support these operations. However, Burn seems to lack support for them.

For me, if bitwise operations were available, I could easily implement NumPy's packbits and unpackbits functions in Burn. These functions would help me save 87.5% of the space when storing tensors in one-hot or multi-hot representations.