MLDS 432: Deep Learning



Many challenging problems in diverse areas such as computer vision, speech recognition, and machine language translation have recently made great progress by using an emerging technology called deep learning. At its core, deep learning is inspired by a simplified model of how the human brain works by building effective hierarchical representations of complex data. This course will explore applications and theory relevant to problem-solving using deep learning. By the end of this course, students will gain intuition about how to apply various techniques judiciously and how to evaluate success. Students will also gain deeper insight into why certain techniques may work or fail for certain kinds of problems.​

This course covers deep learning theory and practice. The focus of the course is to expose the students to challenges and opportunities in deep learning through project-based work. The students learn the science and intuition of how to construct deep neural networks, improve the accuracy of models and how to interpret results from the models.

The course objectives are to:

  1. Understand how deep learning models work
  2. Learn techniques to build convolutional neural networks (CNN)
  3. Apply deep learning to time series via recurrent neural networks (RNN)
  4. Understand optimization and backpropagation techniques used in deep learning
  5. Explore how neural networks perceive the world