Crate concision

Source
Expand description

concision aims to be a complete machine-learning toolkit written in Rust. The framework is designed to be performant, extensible, and easy to use while offering a wide range of features for building and training machine learning models.

§Features

  • ndarray: extensive support for multi-dimensional arrays, enabling efficient data manipulation.

§Long term goals

  • DSL: Create a pseudo-DSL for defining machine learning models and training processes.
  • GPU: Support for GPU acceleration to speed up training and inference.
  • Interoperability: Integrate with other libraries and frameworks (TensorFlow, PyTorch)
  • Visualization: Utilities for visualizing model architectures and training progress
  • WASM: Native support for WebAssembly enabling models to be run in web browsers.

Modules§

activate
This module implements various activation functions for neural networks.
data
Datasets and data loaders for the Concision framework.
error
init
This module works to provide the crate with various initialization methods suitable for machine-learning models.
loss
This module provides various loss functions used in machine learning.
nn
The neural network abstractions used to create and train models.
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
utils
A suite of utilities tailored toward neural networks.

Structs§

PadActionIter
An iterator over the variants of PadAction
Padding
ParamsBase
this structure extends the ArrayBase type to include bias

Enums§

Error
PadAction
PadError
PadMode
ParamsError
UtilityError

Traits§

Activate
The Activate trait enables the definition of new activation functions often implemented as fieldless structs.
ActivateGradient
Affine
apply an affine transformation to a tensor; affine transformation is defined as mul * self + add
ApplyGradient
A trait declaring basic gradient-related routines for a neural network
ApplyGradientExt
This trait extends the ApplyGradient trait by allowing for momentum-based optimization
ArrayLike
Backward
Backward propagate a delta through the system;
BinaryAction
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
Codex
CrossEntropy
A trait for computing the cross-entropy loss of a tensor or array
Decode
Decode defines a standard interface for decoding data.
DecrementAxis
This trait enables an array to remove an axis from itself
DefaultLike
DropOut
[Dropout] randomly zeroizes elements with a given probability (p).
Encode
Encode defines a standard interface for encoding data.
FillLike
FloorDiv
Forward
This trait denotes entities capable of performing a single forward step
Heavyside
IncrementAxis
Init
A trait for creating custom initialization routines for models or other entities.
InitInplace
This trait enables models to implement custom, in-place initialization methods.
IntoAxis
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
LinearActivation
MaskFill
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
MeanAbsoluteError
Compute the mean absolute error (MAE) of the object.
MeanSquaredError
Compute the mean squared error (MSE) of the object.
NdActivate
NdActivateMut
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
OnesLike
Pad
PercentDiff
Compute the percentage difference between two values. The percentage difference is defined as:
ReLU
Root
RoundTo
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.
Sigmoid
Softmax
SoftmaxAxis
SummaryStatistics
This trait describes the fundamental methods of summary statistics. These include the mean, standard deviation, variance, and more.
Tanh
Tensor
Transpose
the trait denotes the ability to transpose a tensor
Unsqueeze
ZerosLike

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
floor_div
genspace
heavyside
Heaviside activation function
hstack
inverse
is_similar_pattern
Check if two patterns are similar enough to be considered duplicates
layer_norm
layer_norm_axis
linarr
pad
pad_to
relu
relu_derivative
round_to
Round the given value to the given number of decimal places.
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

Type Aliases§

PadResult
Params
a type alias for owned parameters
ParamsView
a type alias for an immutable view of the parameters
ParamsViewMut
a type alias for a mutable view of the parameters
Result
a type alias for a Result with a Error

Derive Macros§

Keyed
This macro generates a parameter struct and an enum of parameter keys.