Namespace AiDotNet.Helpers
Classes
- ActivationHelper
Provides centralized helper methods for applying activation functions with optimal performance. Uses Engine methods (GPU/SIMD) for known activation types, falls back to standard activation otherwise.
- AdaptiveParametersHelper<T, TInput, TOutput>
Helper class that provides methods for dynamically adjusting genetic algorithm parameters during optimization.
- AudioHelper<T>
Helper class for loading and saving audio as tensors.
- AudioHelper<T>.AudioLoadResult
Result of loading an audio file, including metadata.
- CompressionHelper
Provides transparent compression and decompression utilities for model serialization.
- ConversionsHelper
Provides utility methods for converting between different data structures used in machine learning models.
- DataAggregationHelper
Helper class for aggregating data samples.
- DiffusionNoiseHelper<T>
Helper class for noise sampling operations in diffusion models.
- EnumHelper
Provides utility methods for working with enumeration types.
- GradientClippingHelper
Provides gradient clipping utilities to prevent exploding gradients during training.
- ImageHelper<T>
Helper class for loading and saving images as tensors.
- InputHelper<T, TInput>
Provides helper methods for input-related operations.
- LayerHelper<T>
Provides helper methods for creating various neural network layer configurations.
- MatrixHelper<T>
Provides helper methods for matrix operations used in AI and machine learning algorithms.
- MatrixSolutionHelper
Provides methods for solving linear systems of equations using various matrix decomposition techniques.
- ModelHelper<T, TInput, TOutput>
Provides helper methods for model-related operations.
- NeuralNetworkHelper<T>
Provides helper methods for neural network operations including activation functions and loss functions.
- NumericalStabilityHelper
Provides numerical stability utilities for safe mathematical operations in machine learning.
- OutlierRemovalHelper<T, TInput, TOutput>
Provides helper methods for outlier removal algorithms.
- ParallelProcessingHelper
Helper class for executing multiple tasks in parallel to improve performance.
- RegressionHelper<T>
Helper class that provides common operations for regression analysis.
- SamplingHelper
Provides methods for sampling data, which is essential for many AI and machine learning techniques.
- SerializationHelper<T>
Provides methods for serializing and deserializing AI model components to and from binary formats.
- StatisticsHelper<T>
Provides statistical calculation methods for various data analysis tasks.
- TensorCopyHelper
Helper class for tensor copy operations.
- TextProcessingHelper
Provides text processing utilities for splitting and tokenizing text.
- TimeSeriesHelper<T>
Provides helper methods for time series analysis and forecasting.
- ValidationHelper<T>
Provides validation methods for AI model inputs and parameters.
- VectorHelper
Provides helper methods for creating and manipulating vectors used in AI and machine learning operations.
- WeightFunctionHelper<T>
Provides methods for calculating weights used in robust regression techniques.