MANNAlgorithm<T, TInput, TOutput>
Models & Types · AiDotNet.MetaLearning.Algorithms
Implementation of Memory-Augmented Neural Networks (MANN) for meta-learning.
Inheritance: ModelBase<T, TInput, TOutput> → MetaLearnerBase<T, TInput, TOutput> → MANNAlgorithm<T, TInput, TOutput>
Implements: IGeneratedParameterRegistrar<T>
For Beginners
MANN uses an external memory like a human’s working memory:
How it works:
- Neural network processes input and produces a key
- Uses key to read relevant information from external memory
- Combines input with memory content to make prediction
- During learning, writes new information to memory
- Memory persists across episodes for lifelong learning
Analogy: Like a student with a notebook who can:
- Look up previous examples (reading memory)
- Write down new important information (writing memory)
- Use both to solve new problems
How It Works
Memory-Augmented Neural Networks combine a neural network with an external memory matrix. The network can read from and write to this memory, enabling rapid learning by storing new information directly in memory during adaptation.
Algorithm - Memory-Augmented Neural Networks:
Key Insights:
- Rapid Learning: New information can be stored in memory with a single
write operation, enabling one-shot learning.
- Continuous Learning: Memory persists across episodes, allowing the
model to accumulate knowledge over time.
- Differentiable Memory: Both reading and writing operations are
differentiable, enabling end-to-end training.
Reference: Santoro, A., Bartunov, S., Botvinick, M., Wierstra, D., & Lillicrap, T. (2016). Meta-Learning with Memory-Augmented Neural Networks. ICML.
Constructors
| Constructor | Summary |
|---|---|
MANNAlgorithm(MANNOptions<T, TInput, TOutput> options) |
Initializes a new instance of the MANNAlgorithm class. |
Properties
| Property | Summary |
|---|---|
MetaLearningAlgorithmType AlgorithmType { get; } |
Gets the algorithm type identifier for this meta-learner. |
Methods
| Method | Summary |
|---|---|
IModel<TInput, TOutput, ModelMetadata<T>> Adapt(IMetaLearningTask<T, TInput, TOutput> task) |
Adapts to a new task by writing support examples to a copy of the memory. |
ModelOptions GetOptions() |
|
T MetaTrain(TaskBatch<T, TInput, TOutput> taskBatch) |
Performs one meta-training step using MANN’s episodic training with memory. |