level

torchhd.level(num_vectors: int, dimensions: int, vsa: Literal['BSC', 'MAP', 'HRR', 'FHRR', 'BSBC', 'VTB', 'MCR', 'CGR'] = 'MAP', *, randomness: float = 0.0, requires_grad=False, **kwargs) → VSATensor[source]

Creates a set of level correlated hypervectors.

Implements level-hypervectors as an interpolation between random-hypervectors as described in An Extension to Basis-Hypervectors for Learning from Circular Data in Hyperdimensional Computing. The first and last hypervector in the generated set are quasi-orthogonal.

Parameters:

num_vectors (int) – the number of hypervectors to generate.
dimensions (int) – the dimensionality of the hypervectors.
vsa – (VSAOptions, optional): specifies the hypervector type to be instantiated. Default: "MAP".
randomness (float, optional) – r-value to interpolate between level at 0.0 and random-hypervectors at 1.0. Default: 0.0.
generator (torch.Generator, optional) – a pseudorandom number generator for sampling.
dtype (torch.dtype, optional) – the desired data type of returned tensor. Default: if None depends on VSATensor.
device (torch.device, optional) – the desired device of returned tensor. Default: if None, uses the current device for the default tensor type (see torch.set_default_tensor_type()). device will be the CPU for CPU tensor types and the current CUDA device for CUDA tensor types.
requires_grad (bool, optional) – If autograd should record operations on the returned tensor. Default: False.

Examples:

>>> torchhd.level(5, 6, "BSC")
tensor([[ True,  True,  True,  True, False, False],
        [ True,  True,  True,  True, False, False],
        [False,  True,  True,  True,  True, False],
        [False,  True,  True,  True,  True, False],
        [False,  True,  True,  True,  True, False]])

>>> torchhd.level(5, 6, "MAP")
tensor([[ 1.,  1., -1.,  1., -1.,  1.],
        [ 1.,  1.,  1.,  1., -1.,  1.],
        [ 1.,  1.,  1.,  1., -1.,  1.],
        [ 1.,  1.,  1.,  1.,  1.,  1.],
        [ 1., -1.,  1.,  1.,  1., -1.]])

>>> torchhd.level(5, 6, "FHRR")
tensor([[-0.996+0.079j,  0.447+0.894j, -0.840-0.541j, -0.999+0.020j, -0.742+0.669j, -0.999+0.042j],
        [-0.886-0.462j,  0.447+0.894j, -0.840-0.541j, -0.999+0.020j, -0.742+0.669j, -0.886+0.462j],
        [-0.886-0.462j,  0.447+0.894j, -0.146-0.989j, -0.999+0.020j, -0.350-0.936j, -0.886+0.462j],
        [-0.886-0.462j,  0.507+0.861j, -0.146-0.989j, -0.999+0.020j, -0.350-0.936j, -0.886+0.462j],
        [-0.886-0.462j,  0.507+0.861j, -0.146-0.989j, -0.611-0.791j, -0.350-0.936j, -0.886+0.462j]])