One of today’s most popular areas of research in the field of computation is Artificial Intelligence and in particular, its methods to give computation machines the quality of human intelligence: Machine Learning. Numerous methods and algorithms have been developed, their application yielding performance with great implications to the future of the field and likely the world at large. The 90s saw these developments in ML bring the defeat of a top chess player by a computer and most recently a top player in the even more complex game of Go.
Statistical methods are the foundation of Machine Learning and its successes. For a machine to learn it requires large sets of data and its sorting of these data into categories. These categories, akin to human categories of thought, are what the machines in question are said to know. And of course, large sets of data and their analyses falls within the purview of statistical methods. Predictive modeling is a key example: models are created for the prediction of categories based on new data. This simulates the learning process.
Along the course of this semester I’ve become more aware of the terminology in the methods and applications in this field and have found it tremendously interesting. I’m willing to explore more of the topic and might just pursue opportunities related to Machine Learning after completing this semester and my bachelor’s.
