Course Name: Big Data and Deep Learning
Prerequisites: Linear Algebra, Statistics, Programming
This course will introduce the methods and frontiers in machine learning and data mining, focusing on big data analysis and deep learning. The foundations of machine learning related to artificial intelligence will be introduced, including support vector machine, neural networks, other supervised learning and unsupervised learning methods. The concept and motivation of deep learning will be discussed. The breakthrough methods in deep learning, including auto Encoder, Restricted Boltzmann Machine, Deep Belief Network will be introduced. The course will also discuss big data analysis methods and visualization methods, e.g., distributed stochastic neighborhood embedding etc.. The statistical modeling methods of big data will be introduced. Seven computational methods supporting the analysis of massive data, including basic statistics, generalized N-Body Problems, graph-theoretic computations, and linear algebra methods (e.g., Eigenvalue problem) will be discussed. Take the deep learning research in Google Inc. and recommendation system as examples, the applications of deep learning and big data learning will be introduced.