MANNModel<T, TInput, TOutput>
Models & Types · AiDotNet.MetaLearning.Algorithms
MANN model for inference with external memory.
Implements: IModel<TInput, TOutput, ModelMetadata<T>>
Constructors
| Constructor | Summary |
|---|---|
MANNModel(IFullModel<T, TInput, TOutput> controller, ExternalMemory<T> memory, MANNOptions<T, TInput, TOutput> options, INumericOperations<T> numOps) |
Initializes a new instance of the MANNModel. |
Properties
| Property | Summary |
|---|---|
ModelMetadata<T> Metadata { get; } |
Gets the model metadata. |
Methods
| Method | Summary |
|---|---|
ModelMetadata<T> GetModelMetadata() |
Gets model metadata. |
TOutput Predict(TInput input) |
Makes predictions using memory-augmented classification: one row per example, the output layer applied to the example’s own controller features and a read of the memory with them as the key - softmax probabilities, or logits when `UseOutput… |
Vector<T> GetParameters() |
Gets the controller’s parameters followed by the output layer’s weights and bias (once the layer exists). |
void Train(TInput inputs, TOutput targets) |
Training is not supported for adapted models. |
void UpdateParameters(Vector<T> parameters) |
Parameter updates are not supported for adapted models. |