Machine learning is the science that enables computers to perform tasks without having to be programmed. Machine learning has enabled self-driving cars and practical speech recognition. It also allows for effective web searches, improved understanding of the human genome, and machine learning has made it possible to create machine-learning algorithms. Machine learning is so common that many people use it every day, even though they don't know it. It is also believed to be the best way for human-level AI. This class will teach you the best machine learning techniques and give you the opportunity to put them into practice. You will not only learn the theoretical foundations of learning but also the practical skills required to apply these techniques quickly and effectively to new problems. You'll also learn about the best practices of innovation in Silicon Valley when it comes to machine learning or AI.
This course will provide a general introduction to machine learning, statistical pattern recognition, and datamining. Topics include: (i) Supervised learning (parametric/non-parametric algorithms, support vector machines, kernels, neural networks). (iii) Unsupervised Learning (clustering (dimensionality reduction), recommender systems and deep learning). (iii). Best practices in machine-learning (bias/variance theories; innovation process in machinelearning and AI). You will also be able to draw on numerous case studies and examples to learn how to use learning algorithms to build smart robots (perception and control), text understanding (websearch, anti-spam), medical informatics, computer vision, and other areas.
