Introduction to Deep Learning

Deep Learning is a cutting-edge technique for many applications, from natural language processing to biomedicine. Deep Learning can handle many different types of data, such as images, text, voice/sound, graphs, etc. This course covers the fundamentals of Deep Learning, including building and training multilayer perceptrons, convolutional neural networks (CNNs), recurrent neural networks (RNNs), autoencoders (AEs), and generative adversarial networks (GANs). The course includes several hands-on projects, including detecting cancer with a CNN, using RNNs on disaster tweets, and generating dog images with a GAN. Prior knowledge of coding or scripting is required. We will use Python extensively throughout the course. We recommend reading the two previous courses in this specialization, Introduction to Machine Learning: Supervised Learning and Unsupervised Algorithms in Machine Learning, but they are not required. College-level math skills are required, including Calculus and Linear Algebra. Some portions of the course will be relatively math intensive. This course may be taken for academic credit toward CU Boulder’s MS in Data Science or MS in Computer Science programs, both offered on Coursera. These fully accredited degrees offer focused courses, short 8-week sessions, and tuition-based programs. Admission is based on three prerequisite courses, not academic history. CU degrees on Coursera are ideal for recent graduates or working professionals. Learn more: MS in Data Science: https://www.coursera.org/degrees/master-of-science-data-science-boulder MS in Computer Science: https://coursera.org/degrees/ms-computer-science-boulder Course logo image by Ryan Wallace on Unsplash.