SEALAlgorithm<T, TInput, TOutput>
Models & Types · AiDotNet.MetaLearning.Algorithms
Implementation of the SEAL (Sample-Efficient Adaptive Learning) meta-learning algorithm.
Inheritance: ModelBase<T, TInput, TOutput> → MetaLearnerBase<T, TInput, TOutput> → SEALAlgorithm<T, TInput, TOutput>
Implements: IGeneratedParameterRegistrar<T>
For Beginners
SEAL learns the best starting point for a model so that it can quickly adapt to new tasks with minimal data.
Imagine learning to play musical instruments:
- Learning your first instrument (e.g., piano) is hard
- Learning your second instrument (e.g., guitar) is easier
- By the time you learn your 5th instrument, you’ve learned principles of music
that help you pick up new instruments much faster
SEAL does the same with machine learning models - it learns from many tasks to find a great starting point that makes adapting to new tasks much faster.
How It Works
SEAL is a gradient-based meta-learning algorithm that combines ideas from MAML with sample-efficiency improvements. It learns initial parameters that can be quickly adapted to new tasks with just a few examples.
Key Features:
- Temperature scaling: Controls confidence in predictions during meta-training
- Entropy regularization: Encourages diverse predictions to prevent overconfident models
- Adaptive learning rates: Per-parameter learning rate adaptation based on gradient norms
- Weight decay: Prevents overfitting to meta-training tasks
Algorithm:
- Sample a batch of tasks
- For each task:
a. Clone the meta-model b. Adapt to the task using support set (inner loop) c. Evaluate on query set to compute meta-loss d. Apply temperature scaling and entropy regularization e. Compute meta-gradients
- Average meta-gradients across tasks
- Apply weight decay and update meta-parameters
Reference: Based on gradient-based meta-learning with additional efficiency improvements including temperature scaling and entropy regularization.
Constructors
| Constructor | Summary |
|---|---|
SEALAlgorithm(SEALOptions<T, TInput, TOutput> options) |
Initializes a new instance of the SEALAlgorithm 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 the meta-learned model to a new task using gradient descent. |
T MetaTrain(TaskBatch<T, TInput, TOutput> taskBatch) |
Performs one meta-training step using SEAL’s sample-efficient approach. |