UniTSOptions<T>
Options & Configuration · AiDotNet.Models.Options
Configuration options for UniTS (Unified Time Series Model).
Inheritance: ModelOptions → RegressionOptions<T> → TimeSeriesRegressionOptions<T> → UniTSOptions<T>
For Beginners
UniTS is designed to be a universal time series model:
The Key Insight: Different time series tasks share common patterns. Instead of training separate models, UniTS learns a unified representation that works for all tasks.
Supported Tasks:
- Forecasting: Predict future values
- Classification: Categorize entire time series
- Anomaly Detection: Identify unusual patterns
- Imputation: Fill in missing values
Architecture:
- Multi-scale temporal convolution for local patterns
- Transformer layers for global dependencies
- Task-specific heads for different outputs
- Shared backbone pretrained on diverse datasets
Advantages:
- One model for multiple tasks (transfer learning)
- Strong zero-shot performance on new domains
- Efficient inference (shared computation)
How It Works
UniTS is a unified architecture for multiple time series tasks including forecasting, classification, anomaly detection, and imputation using a single pretrained model.
Reference: Gao et al., “UniTS: A Unified Multi-Task Time Series Model”, 2024.
https://arxiv.org/abs/2403.00131
Constructors
| Constructor | Summary |
|---|---|
UniTSOptions() |
Initializes a new instance of the UniTSOptions class with default values. |
UniTSOptions(UniTSOptions<T> other) |
Initializes a new instance by copying from another instance. |
Properties
| Property | Summary |
|---|---|
double DropoutRate { get; set; } |
Gets or sets the dropout rate for regularization. |
int ContextLength { get; set; } |
Gets or sets the context length (input sequence length). |
int ForecastHorizon { get; set; } |
Gets or sets the forecast horizon (prediction length). |
int HiddenDimension { get; set; } |
Gets or sets the hidden dimension. |
int NumClasses { get; set; } |
Gets or sets the number of classes for classification task. |
int NumHeads { get; set; } |
Gets or sets the number of attention heads. |
int NumLayers { get; set; } |
Gets or sets the number of transformer layers. |
int[] ConvKernelSizes { get; set; } |
Gets or sets the convolution kernel sizes for multi-scale temporal convolution. |
string TaskType { get; set; } |
Gets or sets the task type. |