Houdini 21.0 Nodes Geometry nodes

ML Regression Kernel geometry node

Determine an output based on a kernel model that optimally fits given labeled examples.

On this page

Overview

This node computes a kernel model. This model consists of a weighted average of kernel functions centred at input components of labeled examples. The model is parameterized by the weights of the kernel functions. This provides an alternative to inferencing a trained neural network. In situation where a kernel model is suitable, ML Regression Kernel provides a simpler alternative to training and inferencing a neural network.

The first input of ML Regression Kernel should consist of labeled examples. For example, created using ML Example inside a SOP for loop or read in from a file using ML Example Import. The second input should be an input component with the same contributions as each input component of the labeled examples. The input/output contributions that are specified by the multi parameter should match the input/target contributions specified on the ML nodes from the origin labeled examples.

When ML Train Regression and ML Regression Inference is preferred, ML Regression Kernel can be useful for verifying the data set was correctly generated. If you give an input component of a labeled example of the data set, ML Regression Kernel should return an exact match for the target. This assumes no two labeled examples in the data set have the same input component.

See Machine Learning documentation for more general information.

Parameters

Batch

In Single mode, a single input is evaluated. In Multiple Packed mode, the model is evaluated on each embedded geometry of the input and the results are stored in corresponding packed primitives.

Weight Decay

The model trained by this node minimizes a quadratic loss. Weight Decay is a coefficient that scales a sum of squared weights (excluding bias parameters) that is a summand of this loss. Increasing the Weight Decay may improve the generalization of the model, while sacrificing how closely it fits the example targets. Increasing the value of this parameter may also help you get a more stable solution in cases that are difficult to train.

Error Threshold

This is a relative error threshold that is used to detect cases where the solution is not accurate enough. If the error of the computed model exceeds this threshold, then the node will display an error. This threshold doesn’t really do anything except generating errors when it is exceeded. This is to avoid surprises when an accurate model cannot be computed.

Kernel Type

This determines the type of kernel function that the model is based on. The kernel maps each pair of input components to a value.

Gaussian

Exponential function of a scaled, negated squared distance of two inputs.

Polynomial

Takes the dot product of two inputs, adds a constant to it and then raises the result to a specified degree.

Sigmoid

Takes the dot product of two inputs, multiplies that by a constant, adds another constant, and then applies a hyperbolic tangent.

Width

When in Gaussian, missing description.

Polynomial Offset

When in Polynomial, missing description.

Polynomial Offset

When in Polynomial, missing description.

Sigmoid Scale

When in Sigmoid, missing description.

Sigmoid Offset

When in Sigmoid, missing description.

–>

Number of Inputs

Type

Type of input contribution: either a point attribute or a volume.

Point Attribute

Name of a point float attribute.

Volume Name

The name of a volume.

Volume Resolution

Resolution of the volume.

Tuple Size

Tuple size of the point attribute or volume.

Number of Outputs

Type

Type of target contribution: either a point attribute or a volume.

Point Attribute

Name of a point float attribute.

Volume Name

The name a the volume.

Volume Resolution

Resolution of the volume.

Tuple Size

Tuple size of the point attribute or volume.

Inputs

Labeled Examples

The labeled examples whose input components will be compared to the query input component.

Input Component

The query input component.

Outputs

Output Component

The output component that corresponds to the labeled example that matches the query input component.

Geometry nodes