Course Objective
Understand the fundamentals of Artificial Intelligence (AI) and its applications in embedded systems. Learn to develop AI-enabled embedded applications using machine learning and edge AI techniques. Integrate AI algorithms with microcontrollers and embedded hardware for intelligent decision-making. Optimize AI models for real-time, low-power, and resource- constrained embedded devices. Design and implement smart embedded systems for IoT, robotics, industrial automation, and intelligent edge applications.
Course Structure
The course is designed as an 8-credit program, with a total duration of 180 hours. (Theory 60 and Practical 120) Classes will be conducted six days a week (Monday to Saturday). Each day will comprise 2 hours of theory lectures followed by 2 hours of practical laboratory sessions, providing learners with a balanced combination of conceptual knowledge and hands-on experience.
Course Eligibility
Second Year B.Sc. (Electronics/Computers), Diploma (E&TC/Computer), Second Year B.E. (E&TC), or higher, undergoing/completed.
Prerequisite
Must have basic knowledge of C++ Programming and must have completed (Microcontroller Programming & Interfacing)
Course Content
Programming Crash Course
Python: Basics, Loops, Blocks and Statements, Lists, Sets, File I/O, Modules and Functions, OOP’s concepts. Keras: Introduction, Installation, and Configuration; TensorFlow: Tensors, TensorFlow Installation, TensorFlow basics.
Machine Learning
Introduction. Supervised Machine Learning: Data gathering, Data Cleaning, Data Labelling, Build ML models using Python, Training and Testing the models.
Algorithms – Linear and Nonlinear classification, Regression Techniques, Decision Trees, Oblique trees, Random Forest, Bayesian analysis and Naive Bayes classifier. Algorithm Performance. Unsupervised Machine Learning Text Classification using Python and NLTK / Naive Bayes.
Deep Learning
Introduction to Neural Networks, Deep Neural Networks, Perceptrons, RNN, CNN, LSTM, Deep Belief Network, Semantic Hashing, Building Deep Learning Models / Neural Networks using Keras and TensorFlow, Testing and Training the models Convolutional Neural Networks
AI in the Automobile Industry
Introduction, Applications of AI in the Automobile Industry, Computer Vision, NLP, Autonomous Driving, Sensors, Cameras, Gathering and Processing Data from Devices / Sensors, Vehicle Control Systems, Decision Making, Automatic Navigation
Admission and Selection Process
The application form is available on the website. Candidates must submit the completed application form and appear for the Common Entrance Test (CET), which will be conducted offline at our centre. The CET syllabus and assessment will be based on the specific course module selected by the candidate. Candidates who successfully complete the written assessment will be required to appear for a Viva Voce (oral interview) as part of the admission process. Final selection will be based on the candidate’s performance in both the CET and the Viva Voce.
Fee Structure
Course Fees: Rs.22,000/
