This course will introduce you to Deep Learning and Reinforcement Learning, two of the most popular disciplines in Machine Learning. Deep Learning is a subset in Machine Learning. It is used in both Supervised as well as Unsupervised Learning and is often used to power many of the AI applications we use every day. You will first learn about Neural Networks and the modern architectures of Deep Learning. After you have created a few Deep Learning models the course will move on to Reinforcement Learning. This type of Machine Learning has been getting more attention lately. While Reinforcement learning has very few applications currently, it is an area of AI research that could be relevant in the future.
If you've completed the IBM Specialization courses in sequence, this course will give you a lot of practice and a solid knowledge of the main types and methods of Machine Learning. These include: Unsupervised Learning, Deep Learning and Supervised Learning. By the end of this course you should be able to: Explain the kinds of problems suitable for Unsupervised Learning approaches Explain the curse of dimensionality, and how it makes clustering difficult with many features Describe and use common clustering and dimensionality-reduction algorithms Try clustering points where appropriate, compare the performance of per-cluster models Understand metrics relevant for characterizing clusters Who should take this course? This course is for data scientists who are interested in learning hands-on skills with Deep Learning and Reinforcement Learning. What skills are required? You should be familiar with Python programming and have a basic understanding of Data Cleaning, Exploratory Data Analysing, Unsupervised Learning, Supervised Learning.
