Machine Learning with Spark

Abstract

Interest in machine learning is growing by leaps and bounds. It has gained a lot of momentum in recent years for a few reasons. The first reason is performance improvements in hardware and algorithms. Machine learning is compute-intensive. With proliferation of multi-CPU and multi-core machines and efficient algorithms, it has become feasible to do machine learning computations in reasonable time. The second reason is that machine learning software has become freely available. Many good quality open source machine learning software are available now for anyone to download. The third reason is that MOOCs (massive open online courses) have created tremendous awareness about machine learning. These courses have democratized the knowledge required to use machine learning. Machine learning skills are no longer limited to a few people with Ph.D. in Statistics. Anyone can now learn and apply machine learning techniques.