Struct Reptile 

pub struct Reptile { /* private fields */ }

Reptile meta-learning algorithm.

Reptile is a simpler first-order algorithm that:

1. Samples a task
2. Trains on it via SGD to get φ
3. Updates θ ← θ + ε(φ - θ)

Implementations

impl Reptile

pub fn new(config: ReptileConfig) -> Self

Create a new Reptile meta-learner.

Trait Implementations

impl Clone for Reptile

fn clone(&self) -> Reptile

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for Reptile

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for Reptile

fn default() -> Self

Returns the “default value” for a type.

impl MetaLearner for Reptile

fn meta_step( &self, tasks: &[MetaTask], parameters: &HashMap<String, Array1<f64>>, ) -> TrainResult<(HashMap<String, Array1<f64>>, f64)>

Perform one step of meta-training on a batch of tasks.

fn adapt( &self, task: &MetaTask, parameters: &HashMap<String, Array1<f64>>, ) -> TrainResult<HashMap<String, Array1<f64>>>

Adapt parameters to a specific task (inner loop).