ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING(AI & ML) - 4 YEARS
An AI and ML course aims to equip learners with a deep understanding of artificial intelligence and machine learning fundamentals, including their history, theories, and practical applications. Starting with an introduction to AI, the course covers its evolution, foundational principles, and diverse applications across various industries. It progresses to in-depth discussions on machine learning, introducing core concepts, types of learning (supervised, unsupervised, and reinforcement learning), and essential tools and libraries like TensorFlow and PyTorch. The curriculum delves into data handling, featuring techniques for data collection, cleaning, visualization, and feature engineering, setting the stage for advanced modules on deep learning. Topics under deep learning encompass artificial neural networks, convolutional neural networks (CNNs), and recurrent neural networks (RNNs), alongside practical insights into model evaluation, selection, and deployment.
Beyond theoretical knowledge, the course emphasizes hands-on learning through lab sessions and projects that apply AI and ML concepts to real-world scenarios, reinforcing the theoretical foundation with practical experience. It addresses model overfitting, regularization, and the ethics of AI, ensuring learners not only build robust models but also consider fairness and transparency in their applications. Advanced topics like reinforcement learning and current trends in AI research are discussed, preparing students for the evolving landscape of AI technologies. Assessments through quizzes, assignments, and a capstone project ensure a comprehensive understanding and application of AI and ML principles, making this course a solid foundation for anyone looking to enter or advance in the field of artificial intelligence and machine learning.
Beyond theoretical knowledge, the course emphasizes hands-on learning through lab sessions and projects that apply AI and ML concepts to real-world scenarios, reinforcing the theoretical foundation with practical experience. It addresses model overfitting, regularization, and the ethics of AI, ensuring learners not only build robust models but also consider fairness and transparency in their applications. Advanced topics like reinforcement learning and current trends in AI research are discussed, preparing students for the evolving landscape of AI technologies. Assessments through quizzes, assignments, and a capstone project ensure a comprehensive understanding and application of AI and ML principles, making this course a solid foundation for anyone looking to enter or advance in the field of artificial intelligence and machine learning.
Eligibility:
The candidates should have secured a minimum of 45% marks in aggregates (40% marks in case of SC/ST candidates) in three subjects with Physics, Mathematics as Compulsory Subject and any one of Chemistry / Biology / Bio-Chemistry / Computer Science / Electronics and shall have completed PUC 10+2 or its equivalent with English as one of the Subject.