About the Course
This course on ‘Artificial Intelligence and Edge Computing’ is a first level course for aspiring engineers of Edge Computing/IoT/AI developers to acquire practice-based AI/Machine Learning skills and Edge Computing fundamentals. The course has been designed with a clear vision on future developments of Edge Computing in industrial applications along with a mission of importing all essential learning fundamentals for the undergraduate engineers. The course has been weaved with necessary fundamentals of applied mathematics and python programming to inculcate the practicing skills of design and development of machine learning algorithms. The course contents are meticulously presented so that the learner will be able to visualize the applied areas of ML algorithms and to correlate & decide the preferences among Cloud, Fog and Edge Computing. The concepts on the designing of Edge Computing Systems are provided with perfect demonstrations through TensorFlow and TensorFlow lite frameworks, which provide complete learner engagement. During the course, the instructional model is designed to ensure that the learner has opportunities to explore modular tasks using retrospectives and to gain Higher order thinking skills. The course elevates the learner’s practical experience using edge computing hardware demos. The learners will also be assured with the outcomes by executing an in-course project module.
Course Objective
  • Introduce composite relational model of edge computing along with AI, Machine Learning and IoT
  • Impart the ML and IoT frameworks suitable for Edge Computing
  • Elevate the learners with a knowledge and practice on tools supporting for Edge Computing solutions
  • Offer pilot training on modular development boards of Tiny ML
Key Topics
Learning Outcomes
  • Relate the AI, ML and Python programming in the context of Edge Computing
  • Model Python based ML solutions for simple applications
  • Develop ML and IoT frameworks for EC architecture
  • Defend for various ML algorithms and CNNs for their compatibility with EC
  • Estimate appropriate Tiny ML capable, hardware and software tools
  • Adapt EC based architecture for various Engineering applications of Civil, Electrical and Mechanical domains