RTMNU · Third Year B.Tech Computer Science & Engineering (AI & ML) · NEP 2020
Artificial Intelligence & Machine Learning
BCSEAI&ML5T18.3 · Elective I · Semester V · 3 credits · College 30 + university 70
One of the Elective I options.
Unit 1: Introduction to AI & ML
7 hoursAI and its applications, history and evolution; narrow, general and super AI; machine learning and its types — supervised, unsupervised and reinforcement; AI versus ML versus deep learning; applications in healthcare, finance and industry.
Examined in the 70-mark end-semester paper
- What AI is and its history
- Narrow, general and super AI
- What machine learning is
- Types of learning
- Applications of AI
Unit 2: Data Preprocessing & Exploratory Data Analysis (EDA)
8 hoursData collection and datasets; data cleaning, handling missing values and outlier detection; feature selection and engineering; normalisation and scaling; EDA with visualisation and correlation analysis; the train–test split.
Examined in the 70-mark end-semester paper
- Handling missing data
- Outlier detection: z-score and IQR
- Feature engineering
- Feature selection: filter, wrapper and embedded methods
- Normalisation and standardisation
- Exploratory data analysis
Unit 3: Supervised Learning Algorithms
7 hoursLinear and multiple regression; logistic regression, k-nearest neighbours, decision trees and naive Bayes; the confusion matrix, accuracy, precision, recall and F1-score; overfitting and underfitting.
Examined in the 70-mark end-semester paper
- Simple and multiple linear regression
- Logistic regression
- K-nearest neighbours
- Decision tree learning and overfitting
- Bayesian learning and naive Bayes
- Classification metrics
- Bias-variance trade-off
Unit 4: Unsupervised Learning
7 hoursK-means and hierarchical clustering; dimensionality reduction with principal component analysis; the basic idea of association rule learning.
Examined in the 70-mark end-semester paper
- K-means and choosing k
- Hierarchical clustering
- Principal component analysis
- Association rules and Apriori
Unit 5: Introduction to Advanced AI Concepts
7 hoursBasics of neural networks and deep learning; overviews of natural language processing and computer vision; ethical issues and future trends in AI.
Examined in the 70-mark end-semester paper
- Perceptron and multilayer networks
- Feed-forward network architectures
- Levels and challenges of NLP
- Computer vision pipeline
- What AI ethics is and why it matters
- Generative AI
Unit contents are summarised from the official RTMNU syllabus . AiCanCode.org is not affiliated with Rashtrasant Tukadoji Maharaj Nagpur University (RTMNU).