MXNetapache/incubator-mxnet Archived
Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Go, JavaScript and more.
61 libraries, 25 updated this year
Julia's packages are small and composable, so the section reads like a toolbox. Flux is the main deep learning library and Knet an older alternative; MLJ gives classical models a common interface the way scikit-learn does in Python. The JuliaStats organisation supplies Distributions, GLM, MultivariateStats, HypothesisTests and Clustering.
61 libraries
Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Go, JavaScript and more.
Deep Learning framework for Julia inspired by Caffe.
A Julia package for probability distributions and associated functions.
A Julia package for fitting (statistical) mixed-effects models.
Digital Signal Processing (filtering, periodograms, spectrograms, window functions).
Methods for dimensionality reduction.
Basic functions for clustering data: k-means, dp-means, etc.
A set of functions to support the development of machine learning algorithms.
Julia package for loading many of the data sets available in R.
A Julia package for manifold learning and nonlinear dimensionality reduction.
Functions and data dependencies for loading various word embeddings
Algorithms for regression analysis (e.g. linear regression and logistic regression).