Expand description
This library provides the core abstractions and utilities for the Concision framework.
§Features
- ParamsBase: A structure for defining the parameters within a neural network.
- Backward: This trait denotes a single backward pass through a layer of a neural network.
- Forward: This trait denotes a single forward pass through a layer of a neural network.
Re-exports§
pub use super::error::ParamsError;pub use super::params::ParamsBase;pub use super::Params;pub use super::ParamsView;pub use super::ParamsViewMut;
Modules§
- activate
- This module implements various activation functions for neural networks.
- data
- Standard datasets to train the models on.
- error
- init
- This module works to provide the crate with various initialization methods suitable for machine-learning models.
- math
- A suite of mathematical tool and utilities tailored toward neural networks.
- ops
- params
- Parameters for constructing neural network models. This module implements parameters using the ParamsBase struct and its associated types. The ParamsBase struct provides:
- prelude
- traits
- types
- utils
Structs§
- Dataset
- PadAction
Iter - An iterator over the variants of PadAction
- Padding
Enums§
Traits§
- Activate
- Activate
Gradient - Affine
- apply an affine transformation to a tensor;
affine transformation is defined as
mul * self + add - Apply
Gradient - A trait declaring basic gradient-related routines for a neural network
- Apply
Gradient Ext - This trait extends the ApplyGradient trait by allowing for momentum-based optimization
- Array
Like - Backward
- Backward propagate a delta through the system;
- Binary
Action - Clip
- A trait denoting objects capable of being clipped between some minimum and some maximum.
- ClipMut
- This trait enables tensor clipping; it is implemented for
ArrayBase - Cross
Entropy - A trait for computing the cross-entropy loss of a tensor or array
- Decrement
Axis - This trait enables an array to remove an axis from itself
- Default
Like - DropOut
- [Dropout] randomly zeroizes elements with a given probability (
p). - Fill
Like - Forward
- This trait denotes entities capable of performing a single forward step
- Heavyside
- Increment
Axis - Init
- A trait for creating custom initialization routines for models or other entities.
- Init
Inplace - This trait enables models to implement custom, in-place initialization methods.
- Into
Axis - Inverse
- this trait enables the inversion of a matrix
- IsSquare
- L1Norm
- a trait for computing the L1 norm of a tensor or array
- L2Norm
- a trait for computing the L2 norm of a tensor or array
- Linear
Activation - Mask
Fill - This trait is used to fill an array with a value based on a mask. The mask is a boolean array of the same shape as the array.
- Matmul
- A trait denoting objects capable of matrix multiplication.
- Matpow
- a trait denoting objects capable of matrix exponentiation
- Mean
Absolute Error - A trait for computing the mean absolute error of a tensor or array
- Mean
Squared Error - A trait for computing the mean squared error of a tensor or array
- NdActivate
- NdActivate
Mut - NdLike
- Norm
- The Norm trait serves as a unified interface for various normalization routnines. At the moment, the trait provides L1 and L2 techniques.
- Numerical
- Numerical is a trait for all numerical types; implements a number of core operations
- Ones
Like - Pad
- ReLU
- Scalar
- The Scalar trait extends the Numerical trait to include additional mathematical operations for the purpose of reducing the number of overall traits required to complete various machine-learning tasks.
- Scalar
Complex - Sigmoid
- Softmax
- Softmax
Axis - Tanh
- Tensor
- Transpose
- the trait denotes the ability to transpose a tensor
- Unsqueeze
- Zeros
Like
Functions§
- calculate_
pattern_ similarity - Calculate similarity between two patterns
- clip_
gradient - Clip the gradient to a maximum value.
- clip_
inf_ nan - concat_
iter - Creates an n-dimensional array from an iterator of n dimensional arrays.
- extract_
patterns - Extract common patterns from historical sequences
- genspace
- heavyside
- Heaviside activation function
- hstack
- inverse
- is_
similar_ pattern - Check if two patterns are similar enough to be considered duplicates
- linarr
- pad
- pad_to
- relu
- relu_
derivative - sigmoid
- the sigmoid activation function: $f(x) = \frac{1}{1 + e^{-x}}$
- sigmoid_
derivative - the derivative of the sigmoid function
- softmax
- softmax_
axis - stack_
iter - Creates a larger array from an iterator of smaller arrays.
- tanh
- tanh_
derivative - tril
- Returns the lower triangular portion of a matrix.
- triu
- Returns the upper triangular portion of a matrix.
- vstack