Big Data and Deep Learning
Course Description
This course will teach students to work on various real-world big data projects using different Big Data tools as a part of solution strategy. The course will provide students’ knowledge and skills to process big data on platforms that can handle the variety, velocity, and volume of data. This comprehensive training on framework provides hands on experience for solving real time industry based big data projects to become an expert in Big Data. In this course we will learn about the basics of deep neural networks, and their applications to various tasks. The course aim is to present the mathematical, statistical, and computational challenges of building stable representations for high-dimensional data.
Course Objectives:
| · | Student will learn how to format data using new technologies and techniques |
| · | Learn about the fundamentals of databases |
| · | Learn basic principles for working with Big Data |
| · | Learn the basic tools for statistical analysis, R and Python, and several machine learning algorithms |
| · | Learn the tools required for building Deep Learning models |
| · | Explore multiple architectures and understand how to fine-tune and continuously improve models |
| · | Learn how the same task can be solved using multiple Deep Learning approaches |
Course Contents:
| · | Introduction/Overview |
| · | Scalability |
| · | Big Data Systems and Programming |
| · | Hadoop |
| · | Tension Flow |
| · | Shallow and Deep Neural Networks |
| · | Explaining and Harnessing Adversarial Example |
| · | Optimization |
| · | Gradient Checking |
| · | Hyperparameter tuning |
| · | Programming Frameworks |
| · | Conditional GAN, CycleGAN |
