ConditionalRandomFieldLayer<T>
Layers · AiDotNet.NeuralNetworks.Layers
Represents a Conditional Random Field (CRF) layer for sequence labeling tasks.
Inheritance: LayerBase<T> → ConditionalRandomFieldLayer<T>
Implements: IShapeContract
For Beginners
A Conditional Random Field (CRF) layer is used when you need to label each item in a sequence while considering how labels relate to each other.
In many sequence tasks, the label for an item depends not just on the item itself, but also on nearby items:
For example, in a sentence like “John Smith lives in New York”:
- Without CRF: Each word might be labeled independently, potentially creating invalid sequences
- With CRF: The model considers that “New” followed by “York” is likely a location name
Think of it like:
- Standard layers ask, “What’s the best label for this word on its own?”
- CRF layers ask, “What’s the best sequence of labels for the whole sentence?”
CRFs are especially useful for tasks like:
- Named entity recognition (finding names of people, organizations, locations)
- Part-of-speech tagging (labeling words as nouns, verbs, etc.)
- Any task where the correct labels form patterns or follow rules
How It Works
A Conditional Random Field (CRF) layer is a specialized neural network layer designed for sequence labeling tasks such as named entity recognition, part-of-speech tagging, and activity recognition. Unlike standard classification layers that make independent predictions for each element in a sequence, CRF layers model the dependencies between labels in a sequence, leading to more coherent predictions. The layer uses the Viterbi algorithm to find the most likely sequence of labels given the input features and learned transition probabilities between labels.
Constructors
| Constructor | Summary |
|---|---|
ConditionalRandomFieldLayer(int numClasses, IActivationFunction<T> scalarActivation) |
Lazy constructor with vector activation — resolves sequenceLength from input.Shape[0] on first Forward. |
ConditionalRandomFieldLayer(int numClasses, IVectorActivationFunction<T> vectorActivation) |
Lazy constructor with vector activation — resolves sequenceLength from input.Shape[0] on first Forward. |
ConditionalRandomFieldLayer(int numClasses, int sequenceLength, IActivationFunction<T> scalarActivation) |
Initializes a new instance of the ConditionalRandomFieldLayer class with a vector activation function. |
ConditionalRandomFieldLayer(int numClasses, int sequenceLength, IVectorActivationFunction<T> vectorActivation) |
Initializes a new instance of the ConditionalRandomFieldLayer class with a vector activation function. |
Properties
| Property | Summary |
|---|---|
bool SupportsTraining { get; } |
Methods
| Method | Summary |
|---|---|
Dictionary<string, string> GetParameterRoles() |
Returns parameter roles for per-role optimizer configuration (e.g., weight decay exemption for biases). |
IReadOnlyList<OutputAxisContract> OutputAxesFor(int inputRank) |
Derived from this type’s [TensorLayout] declarations. |
IReadOnlyList<Tensor<T>> GetTrainableParameters() |
Returns all trainable parameter tensors marked with [TrainableParameter]. |
void ClearGradients() |
|
void ResetState() |
Resets the internal state of the CRF layer. |
void SetDecodeTagConstraints(IReadOnlyList<string> labelNames) |
Derives hard decode-time constraints on the label topology from the label set and applies them to Viterbi decoding, so the layer can never emit a structurally invalid sequence (an orphan I- tag, a sequence starting on I-, an I-X conti… |
void SetTrainableParameters(IReadOnlyList<Tensor<T>> parameters) |
Replaces trainable parameter tensors (e.g., with ParameterBuffer views). |
void UpdateParameters(T learningRate) |
Updates the layer’s parameters using the calculated gradients. |
void ZeroGrad() |
Clears all gradient fields discovered by convention ({paramName}Gradient). |