LSTMNTMController<T, TInput, TOutput>

Models & Types · AiDotNet.MetaLearning.Algorithms

LSTM-based NTM controller implementation with learnable parameters.

Implements: INTMController<T>

How It Works

This controller uses an LSTM cell to process inputs and generate addressing parameters for the NTM memory. The LSTM maintains hidden state across timesteps, enabling sequential reasoning and temporal dependencies.

Architecture:

Constructors

Constructor Summary
LSTMNTMController(NTMOptions<T, TInput, TOutput> options) Initializes a new instance of LSTMNTMController with learnable weights.

Methods

Method Summary
IReadOnlyList<Tensor<T>> GetParameterTensors()
LSTMNTMController<T, TInput, TOutput> Clone() Creates an independent deep copy of this controller, preserving its resolved input width, learned parameters, and recurrent state.
List<NTMAddressingParameters<T>> GenerateReadAddressing(Tensor<T> output)
List<Tensor<T>> GenerateReadKeys(Tensor<T> output)
NTMAddressingParameters<T> GenerateWriteAddressing(Tensor<T> output)
Tensor<T> Forward(Tensor<T> input, List<Tensor<T>> readContents)
Tensor<T> GenerateAddVector(Tensor<T> output)
Tensor<T> GenerateEraseVector(Tensor<T> output)
Tensor<T> GenerateOutput(Tensor<T> output, List<Tensor<T>> readContents)
Tensor<T> GenerateWriteKey(Tensor<T> output)
Vector<T> GetParameters()
void Reset()
void SetParameters(Vector<T> parameters)