![](/sites/default/files/styles/965x543/public/oembed_thumbnails/av4Fwu51_EYoAGPot6mHZ3d4gDvHXzF-MtCa2spJ7tI.jpg?itok=VTvnFImJ)
In this workshop, we will explore Intel(r) Extensions for Scikit-Learn*. See how to leverage optimizations for common machine learning tools in Scikit-Learn. In this hands-on lab, we explore Intel(r) Extensions for Scikit-Learn patching and unpatching - which can be applied from a global to more surgical level to turn on optimizations for as many as 32 optimized functions. Using a patching strategy can ensure that performance is not lost and has big potential for performance gains.
Agenda: Use Cases, Patching CPU
- Module 1 - Motivation – key algorithm accelerations and test harness testing
- Patching – many ways to apply patching from global to surgical: learn how to win/win on the acceleration game with patching
- Module 2 –
- Explore use cases for key algorithms and how to patch I that context, pairwise_distance as a stock portfolio nearest shape finder,
- Exploration of KNN on Forest coverage dataset
- Patching for Unsupervised learning Kmeans on CPU
- Patching for Supervised learning using SVM – Connect4 dataset
- Practicum: Optional– Telco Customer Churn dataset – PCA, KMeans, DBSCAN, and more
- Module 3 – Practicum Optional: Image clustering example – PCA, Kmeans, DBSCAN
- Module 4 – Practicum: Optional: Synthesized galaxies collide, KNeighbors Classifier, Random Forest, (stretch goal pair_wise distance)