Skip to main content

ICS 452 Introduction to Deep Learning

Deep learning is a subset field of machine learning, concerned with solving complex problems using artificial neural networks. Deep learning algorithms learn the underlying features in data, in order to approach the human-level understanding of this data. In this course students will study deep learning algorithms and their applications in computer vision, speech recognition, audio processing, and natural language processing. This course will cover the basic neural networks, deep feedforward networks, convolutional networks, recurrent networks, and recursive networks. Students will use Tensorflow platform to implement their acquired knowledge.


Special information

Note: Students are responsible to both be aware of and abide by prerequisites for ICS courses for which they enroll, and will be administratively dropped from a course if they have not met prerequisites.First day attendance is mandatory.
4 Undergraduate credits

Effective May 10, 2019 to present

Learning outcomes


  • Justify and describe the differences between artificial intelligence, machine learning and deep learning
  • Describe deep feed-forward networks
  • Analyze convolutional networks
  • Investigate recurrent and recursive networks
  • Investigate how to regularize deep learning algorithms in order to obtain good performance
  • Evaluate and compare the different types of deep networks.
  • Design and develop unbiased deep learning models to solve real life problems, such as sentiment analysis, face recognition, natural language processing, and computer vision