Expand description
Neural network building blocks module for SciRS2
This module provides neural network building blocks for SciRS2, including:
- Layers (dense, convolutional, recurrent, etc.)
- Activation functions (ReLU, sigmoid, tanh, etc.)
- Loss functions (MSE, cross-entropy, etc.)
- Optimizers (SGD, Adam, etc.)
- Model architectures and training utilities
- Neural network specific linear algebra operations
- Model evaluation and testing
- Advanced training techniques
Re-exports§
pub use error::Error;pub use error::NeuralError;pub use error::Result;
Modules§
- activations
- Activation functions for neural networks
- augmentation
- Data augmentation module Advanced data augmentation techniques for neural networks
- autograd
- Automatic differentiation module for neural networks.
- bindings
- C/C++ bindings module C/C++ binding generation utilities for neural networks
- callbacks
- Callback system for neural network training
- compression
- Model compression module Model compression utilities for neural networks
- data
- Data loading and processing utilities for neural networks
- distillation
- Knowledge distillation module Knowledge distillation utilities for neural networks
- error
- Error types for the neural network module
- evaluation
- Model evaluation framework
- gpu
- GPU acceleration module (currently CPU fallback) GPU acceleration for neural network operations
- interop
- Framework interoperability module Framework interoperability utilities for neural networks
- interpretation
- Interpretation module Model interpretation utilities for neural networks
- layers
- Neural network layers implementation
- linalg
- Neural network specific linear algebra operations
- losses
- Loss functions for neural networks
- memory_
efficient - Memory-efficient operations module Memory-efficient implementations for neural networks
- mobile
- Mobile deployment module Mobile deployment utilities for neural networks
- model_
evaluation - Enhanced model evaluation module Enhanced model evaluation tools for neural networks
- models
- Neural network model implementations
- optimizers
- Neural network optimizers
- performance
- Performance optimization module Performance optimization utilities for neural networks
- prelude
- Common neural network functionality
- quantization
- Quantization module Quantization support for neural networks
- serialization
- Module for model serialization and deserialization
- serving
- Serving and deployment module Model serving and deployment utilities for neural networks
- training
- Training utilities and infrastructure
- transfer_
learning - Transfer learning module Transfer learning utilities for neural networks
- transformer
- Transformer models implementation
- utils
- Utility functions for neural networks
- visualization
- Visualization tools module Visualization tools for neural networks
- wasm
- WebAssembly module WebAssembly target support for neural networks