scirs2_series/advanced_training.rs
1//! Advanced Training Methods for Time Series
2//!
3//! This module has been refactored into a modular structure for better maintainability
4//! and organization. All original functionality is preserved through re-exports.
5//!
6//! ## Refactored Module Structure
7//!
8//! The advanced training functionality has been organized into focused sub-modules:
9//!
10//! - **Configuration**: Common data structures and configurations
11//! - **Meta-Learning**: MAML and other meta-learning algorithms
12//! - **Neural ODEs**: Continuous-time neural networks with ODE solvers
13//! - **Variational Methods**: VAEs for probabilistic time series modeling
14//! - **Transformers**: Attention-based sequence modeling
15//! - **Hyperparameter Optimization**: Automated parameter tuning
16//! - **Few-Shot Learning**: Prototypical Networks and REPTILE
17//! - **Memory-Augmented Networks**: External memory architectures
18//! - **Meta-Optimization**: Learned optimizers for adaptive updates
19//!
20//! ## Usage
21//!
22//! All original APIs are preserved. You can continue to use this module exactly
23//! as before:
24//!
25//! ```rust
26//! use scirs2_series::advanced_training::{MAML, TimeSeriesVAE, TimeSeriesTransformer};
27//!
28//! // Create a MAML instance
29//! let mut maml = MAML::<f64>::new(4, 8, 2, 0.01, 0.1, 5);
30//!
31//! // Create a VAE for time series
32//! let vae = TimeSeriesVAE::<f64>::new(10, 3, 5, 16, 16);
33//!
34//! // Create a transformer for forecasting
35//! let transformer = TimeSeriesTransformer::<f64>::new(12, 6, 64, 8, 4, 256);
36//! ```
37//!
38//! ## Advanced Usage
39//!
40//! For more specific functionality, you can also import directly from sub-modules:
41//!
42//! ```rust
43//! use scirs2_series::advanced_training::few_shot::{PrototypicalNetworks, REPTILE};
44//! use scirs2_series::advanced_training::hyperparameter_optimization::{
45//! HyperparameterOptimizer, OptimizationMethod
46//! };
47//! ```
48
49// Re-export the entire modular structure
50pub use self::advanced_training_modules::*;
51
52// Import the modular implementation
53#[path = "advanced_training_modules/mod.rs"]
54mod advanced_training_modules;