-

Make recurrent layers in Flux much faster

Self-concordant Smoothing for Large-Scale Convex Composite Optimization

A package for working with BioVisionHierarchy files (motion capture data)

-

This is a dimensionality reduction algorithm which has the goal of maintaining interpretability i.e we eliminate variables directly from potential models that don't seem to add any predictive power.

-

Explores representations based on bag words

Unfolded convolutional learning for motif discovery

-

Adds support for parallelization for Taija packages.

Julia implementation of AlphaFold 2's Invariant Point Attention

Jet transform operators that depend on FFTW.jl, and Wavelets.jl. Part of the COFII framework.

Pilot library for NLP convolutional nets in Julia