Machine Learning with Swift

Multilinear-math

The name refers to the tensor operations that this library provides. It also contains a set of machine learning and AI primitives. Its algorithms include principal component analysis, multilinear subspace learning algorithms for dimensionality reduction, linear and logistic regression, stochastic gradient descent, feedforward neural networks, sigmoid, ReLU, Softplus activation functions, and regularizations.

It also provides a Swift interface to the Accelerate framework and LAPACK, including vector and matrix operations, eigen decomposition, and SVD. On top of that, it implements the MultidimensionData protocol to work with multidimensional data.

GitHub repository: https://github.com/vincentherrmann/multilinear-math