RTMNU Final E&TC syllabus

RTMNU · Final Year B.Tech Electronics & Telecommunication Engineering · CBCS

Artificial Intelligence

BEETC801PE · Elective VI · Semester VIII · 4 credits · College 30 + university 70

One of the Elective VI options.

  1. Unit 1: Introduction to Artificial Intelligence

    9 hours

    What AI is, its history and its place in society; agents and knowledge-based systems; components of AI.

    Examined in the 70-mark end-semester paper

    • Artificial intelligence: definition and history
    • Intelligent agents and their types
    • Knowledge-based agents and the wumpus world
    • AI applications across sectors
  2. Unit 2: Propositional Logic

    9 hours

    Propositional and first-order logic and their limits; search, games and problem solving; reasoning with uncertainty.

    Examined in the 70-mark end-semester paper

    • Propositional logic and theorem proving
    • First-order logic
    • Problem-solving agents and state-space search
    • Minimax and alpha–beta pruning
    • Inference and uncertainty in expert systems
  3. Unit 3: Machine Learning

    10 hours

    Supervised, unsupervised and reinforcement learning; model-based learning, regression, decision trees, linear discrimination, kernel machines and graphical models.

    Examined in the 70-mark end-semester paper

    • Supervised, unsupervised, semi-supervised and ensemble learning
    • Reinforcement learning basics
    • Linear and logistic regression
    • Decision trees and random forests
    • Generative and discriminative learning paradigms
    • Bayesian networks and the EM algorithm
  4. Unit 4: Artificial Neural Networks and Deep Learning

    10 hours

    Biological and artificial neural networks, the Hopfield network, neural associative memory, linear networks, the back-propagation algorithm, support vector machines and the basics of deep learning.

    Examined in the 70-mark end-semester paper

    • Biological and artificial neurons
    • Hopfield networks and associative memory
    • Backpropagation and support vector machines
    • Deep feedforward networks
  5. Unit 5: Platforms, Tools, Frameworks and Languages for AI and ML

    10 hours

    AI/ML platforms — Salesforce Einstein, IBM Watson, Azure Machine Learning Studio and others; ML tools such as TensorFlow, Amazon ML, Apache Mahout and scikit-learn; languages — Python, R, Java, Julia and C/C++; libraries such as Keras, PyTorch and Caffe.

    Examined in the 70-mark end-semester paper

    • AI and ML platforms: IBM Watson, Azure ML and Salesforce Einstein
    • TensorFlow basics
    • Keras and PyTorch
    • Programming languages for AI: Python, R, Java and Julia

Unit contents are summarised from the official RTMNU syllabus . AiCanCode.org is not affiliated with Rashtrasant Tukadoji Maharaj Nagpur University (RTMNU).