Crate concision_core

Core abstractions and utilities for machine learning.

Re-exports

pub use super::gradient::*;

pub use super::patterns::*;

pub use super::tensor::*;

Modules

activate

This module implements various activation functions for neural networks.

data

this module implements a dataset abstraction for machine learning tasks.

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

PadActionIter

An iterator over the variants of PadAction

Padding

ParamsBase

this structure extends the ArrayBase type to include bias

Enums

Error

PadAction

PadError

PadMode

Traits

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

A simple trait denoting a single backward pass through a layer of a neural network; the trait

Clip

ClipMut

This trait enables tensor clipping; it is implemented for ArrayBase

CrossEntropy

DecrementAxis

This trait enables an array to remove an axis from itself

DefaultLike

DropOut

[Dropout] randomly zeroizes elements with a given probability (p).

FillLike

Forward

This trait defines the forward pass of the network

Heavyside

IncrementAxis

Init

The Init trait is a consuming initialization method

InitInplace

A trait for initializing an object in-place

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

MeanSquaredError

NdActivate

NdActivateMut

NdLike

Norm

OnesLike

Pad

Predict

This trait defines the prediction of the network

ReLU

Sigmoid

Softmax

SoftmaxAxis

Tanh

Train

This trait defines the training process for the network

Transpose

the trait denotes the ability to transpose a tensor

Unsqueeze

ZerosLike

Functions

heavyside

Heaviside activation function

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

tanh

tanh_derivative

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