multiset

torchhd.multiset(input: VSATensor) → VSATensor

Multiset of input hypervectors.

Bundles all the input hypervectors together.

\[\bigoplus_{i=0}^{n-1} V_i\]

Note

This operation does not normalize the resulting or intermediate hypervectors. Normalized hypervectors can be obtained with normalize().

Parameters:

input (VSATensor) – input hypervector tensor

Shapes:

• Input: \((*, n, d)\)

• Output: \((*, d)\)

Examples:

>>> x = torchhd.random(3, 6)
>>> x
tensor([[-1., -1.,  1., -1.,  1., -1.],
        [-1.,  1., -1.,  1., -1.,  1.],
        [-1., -1.,  1., -1.,  1., -1.]])
>>> torchhd.multiset(x)
tensor([-3., -1.,  1., -1.,  1., -1.])