As a general purpose machine learning library for classification, regression, and clustering algorithms, scikit-learn* has many real-world applications. For example, support-vector machines (SVMs), random decision forests, gradient boosting, K-means clustering, and the density-based spatial clustering of applications with noise (DBSCAN), which is a data-clustering algorithm.
Unfortunately, the scikit-learn library by Python* is inherently slow on hardware without additional software optimizations.
Enter the Intel® Extension for Scikit-learn*, part of the Intel® AI Analytics Toolkit. In this webinar, AI technical consulting engineer Rachel Oberman discusses this library, including:
- How it can speed up scikit-learn in just two lines of code, delivering at least 2x better performance
- How to improve scikit-learn memory access
- An overview to get started and a census use case