GTU Study
KHUDKIBOOK
AI & ML
FREE PDF
DI05000051
Code: DI05000051
Credits: 4
Semester 5
Marine
AI & ML
Get the full GTU study material, English & Gujarati textbook PDFs, syllabus curriculum, and solved previous year question papers.
×
English Book & Chapters
English Book Coming Soon
We are working hard to add this material. Stay tuned for updates!
Follow on Instagram for Updates
×
GTU Previous Year Papers
Papers Coming Soon
We are working hard to add this material. Stay tuned for updates!
Follow on Instagram for UpdatesAI & ML Syllabus — Unit-wise Content
The official GTU curriculum for AI & ML (subject code DI05000051) as prescribed for Marine · Semester 5 divides the course into 5 units, covering 14 listed topics. The unit-wise breakdown below is read from the GTU syllabus document for this subject code, so you can check what the course actually covers before deciding which papers to attempt.
Download the official syllabus PDF (DI05000051)Unit 1 1.1 Introduction to Artificial Intelligence
- Definition of Artificial Intelligence Goals and importance of AI Difference between Artificial Intelligence and Machine Learning Examples of AI in daily life (Google Maps
- Netflix recommendation
- chatbots) 1.2 Applications of Artificial Intelligence AI in healthcare AI in finance AI in education AI in manufacturing and automation AI in social media platforms 1.3 AI Development Tools and Libraries Introduction to Python for AI Overview of commonly used libraries: NumPy Program Name: Diploma Engineering Level: Diploma Branch: Electronics & Communication Engineering / Information & Communication Technology Subject Code : DI05000051 Subject Name : AI & ML Pandas Matplotlib Scikit-learn 1.4 Data Handling Using Python Libraries Importing datasets (CSV
- Excel files) using Pandas Basic dataset operations: Viewing data Selecting columns Basic statistical summary 1.5 Data Visualization Using Matplotlib: Line graph Bar chart Pie chart Scatter plot Histogram Using simple real-life or hypothetical datasets. 1.6 Ethical Considerations in AI Bias in AI systems Privacy issues Responsible use of AI Only brief discussion
Unit 2 2.1 Introduction to Machine Learning
- Definition of Machine Learning Difference between traditional programming and machine learning Basic workflow of machine learning o Data collection o Data preprocessing o Model training o Model testing 2.2 Well-Posed Machine Learning Problem Components of ML problem: o Task (T) o Experience (E) o Performance measure (P) Example of well-posed ML problems: o Email spam detection Program Name: Diploma Engineering Level: Diploma Branch: Electronics & Communication Engineering / Information & Communication Technology Subject Code : DI05000051 Subject Name : AI & ML o Movie recommendation o House price prediction 2.3 Types of Machine Learning Supervised Learning Unsupervised Learning Comparison of: Input data Output Applications Examples of: Classification Regression Clustering (concept only) 2.4 Supervised Learning Algorithms Classification Algorithms k-Nearest Neighbours (KNN) Decision Tree (basic concept) Regression Algorithm Linear Regression Applications and simple working principle of each algorithm. 2.5 Model Training and Testing Training dataset Testing dataset Train-test split concept 2.6 Model Evaluation Techniques Basic evaluation concepts: Accuracy Confusion Matrix (simple interpretation) Precision and Recall (basic understanding)
Unit 3 3.1 Introduction to Neural Networks
- Motivation for Neural Networks Biological neuron vs Artificial neuron Applications of Neural Networks: o Image recognition o Speech recognition o Recommendation systems 3.2 Structure of Artificial Neural Networks Components of ANN: Program Name: Diploma Engineering Level: Diploma Branch: Electronics & Communication Engineering / Information & Communication Technology Subject Code : DI05000051 Subject Name : AI & ML o Input layer o Hidden layer o Output layer Basic working of neural networks Concept of weights and bias 3.3 Activation Functions Purpose of activation functions in neural networks
- Common activation functions: Sigmoid function ReLU (Rectified Linear Unit) Tanh function Graphical representation and simple examples. 3.4 Types of Neural Network Architectures Basic introduction to: Single layer neural network Multi-layer neural network Applications and simple working. 3.5 Building a Simple Neural Network Model Using Python libraries such as: Scikit-learn OR Keras (basic introduction) Simple neural network example for classification
- Example datasets: Iris dataset Digit recognition dataset
Unit 4 4.1 Introduction to Natural Language Processing
- Definition of Natural Language Processing Importance of NLP in AI Applications of NLP: o Chatbots o Machine translation o Sentiment analysis o Voice assistants 4.2 NLP Processing Pipeline Basic steps involved in NLP tasks: Text collection Text preprocessing Program Name: Diploma Engineering Level: Diploma Branch: Electronics & Communication Engineering / Information & Communication Technology Subject Code : DI05000051 Subject Name : AI & ML Feature extraction Model building 4.3 Text Preprocessing Techniques Introduction and purpose of preprocessing
- Common preprocessing techniques: Tokenization (word and sentence) Stop word removal Stemming Lemmatization Part-of-Speech (POS) tagging Using NLTK library in Python. 4.4 Text Representation Techniques Methods to convert text into numerical form for machine learning
- Basic techniques: Bag of Words (BoW) Term Frequency (TF) TF-IDF (Term Frequency – Inverse Document Frequency) Simple examples and applications. 4.5 Simple NLP Applications Demonstration of basic NLP tasks such as: Sentiment analysis of text Word frequency analysis Keyword extraction from text Using Python libraries
Unit 5 5.1 Emerging Trends in Artificial Intelligence Overview of modern developments in AI
- Generative AI AI-powered assistants Autonomous systems AI in healthcare
- finance, and education Short real-world case studies. 5.2 Introduction to Generative AI Concept of Generative AI Difference between traditional AI and Generative AI Examples of generative AI systems: o Text generation o Image generation Program Name: Diploma Engineering Level: Diploma Branch: Electronics & Communication Engineering / Information & Communication Technology Subject Code : DI05000051 Subject Name : AI & ML o Code generation Applications in industry. 5.3 Large Language Models (LLMs) Basic introduction to LLMs: What are Large Language Models Examples of LLM-based systems Capabilities of modern AI chat systems: o answering questions o writing code o generating text Applications of LLMs in education
- business, and software development. 5.4 Prompt Engineering Introduction to prompt engineering: What is a prompt Importance of prompt design Basic prompt techniques: o clear instructions o role prompting o step-by-step prompting Types of prompts o Zero-shot prompting o One-shot prompting o Few-shot prompting o Instruction-based prompting o Role-based prompting o Step-by-step (Chain-of-thought) prompting o Creative prompting o Comparative prompting 5.5 Ethical and Responsible AI Discussion on responsible use of AI: Bias in AI systems Data privacy concerns Misuse of AI-generated content Importance of ethical AI development
Study on Android App:
