In this chapter, we explored a few useful techniques to deal with huge amounts of sample data. We also described how we can use machine learning models through online services such as BigML, as follows:
- We described MapReduce and how it is used to process large volumes of data using parallel and distributed computations
- We explored how we can query and persist datasets using the Incanter library and MongoDB
- We briefly studied the BigML cloud service provider and how we can use this service to formulate and evaluate CARTs from sample data
In conclusion, we described several techniques and tools that can be used to implement machine learning systems in this book. Clojure helps us build these systems in a simple and scalable manner by leveraging the power of the JVM and equally powerful libraries. We also studied how we can evaluate and improve machine learning systems. Programmers and architects can use these tools and techniques to model and learn from their users' data, as well as build machine learning systems that provide users with a better experience.
You can explore the academia and research in machine learning through the various citations and references that have been used in this book. New academic papers and articles on machine learning provide even more insight into the cutting-edge of machine learning, and you are encouraged to find and explore them.