Machine Learning

Machine learning has achieved remarkable successes, ranging from the postal service’s handwritten zip code readers to voice recognition systems like Apple’s Siri. These advances also include movie recommendation systems, spam and malware detection, housing price prediction algorithms, and the development of driverless cars. Although Artificial Intelligence (AI) and Machine Learning are terms frequently used interchangeably today, here we distinguish between them. Traditional AI systems, exemplified by chess-playing machines, employed decision-making based on preset rules stemming from theories or fundamental principles. In contrast, machine learning makes decisions using algorithms trained with data. Furthermore, while AI typically refers to tools complete with user interfaces and ready for real-world application, the term Machine Learning is often reserved for the underlying ideas, concepts, and methodologies, regardless of whether a tangible tool has been developed. In this part of the book we focus on these ideas, concepts, and methodologies, but also demonstrate their application to handwritten digits.