NormalInverseGammaLinear

class torch_uncertainty.layers.distributions.NormalInverseGammaLinear(base_layer, event_dim, min_lmbda=1e-06, min_alpha=1e-06, min_beta=1e-06, **layer_args)

Normal-Inverse-Gamma Distribution Linear Density Layer.

Parameters:

• base_layer (type[nn.Module]) – The base layer class.

• event_dim (int) – The number of event dimensions.

• min_lmbda (float) – The minimal value of the $\lambda$ parameter.

• min_alpha (float) – The minimal value of the $\alpha$ parameter.

• min_beta (float) – The minimal value of the $\beta$ parameter.

• **layer_args – Additional arguments for the base layer.

Shape:

• Input: $(\ast ,H_{in})$ where $\ast$ means any number of dimensions including none and $H_{in}=\text{in\_features}$.

• Output: A dict with the following keys

  • "loc": The mean of the Normal-Inverse-Gamma distribution of shape $(\ast ,H_{out})$ where all but the last dimension are the same as the input and $H_{out}=\text{out\_features}$.

  • "lmbda": The lambda parameter of the Normal-Inverse-Gamma distribution of shape $(\ast ,H_{out})$.

  • "alpha": The alpha parameter of the Normal-Inverse-Gamma distribution of shape $(\ast ,H_{out})$.

  • "beta": The beta parameter of the Normal-Inverse-Gamma distribution of shape $(\ast ,H_{out})$.

Source:

• Normal-Inverse-Gamma Distribution