In these previous posts:
- AdaOpt classification on MNIST handwritten digits (without preprocessing) (on 05/29/2020)
- AdaOpt (a probabilistic classifier based on a mix of multivariable optimization and nearest neighbors) for R (on 05/22/2020)
- AdaOpt (on 05/15/2020)
I introduced AdaOpt, a novel probabilistic classifier based on a mix of multivariable optimization and a nearest neighbors algorithm. More details about the algorithm can also be found in this (short) paper. mlsauce’s development version now contains a parallel implementation of AdaOpt. In order to install this development version from the command line, you’ll need to type:
pip install git+https://github.com/Techtonique/mlsauce.git --upgrade
And in order to use parallel processing, create the AdaOpt object (see previous post) with:
n_jobs = 2 # or 4, or -1 or 13