GTU Study
KHUDKIBOOK
ARTIFICIAL INTELLIGENCE &
FREE PDF
2733105
Code: 2733105
Credits: 5
Semester 3
BE
Artificial Intelligence & Expert Systems
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 UpdatesArtificial Intelligence & Expert Systems Syllabus — Unit-wise Content
The official GTU curriculum for Artificial Intelligence & Expert Systems (subject code 2733105) as prescribed for BE · Semester 3 divides the course into 5 units, covering 117 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 (2733105)Unit 1 NEURAL NETWORKS
- Foundations of Neural Networks: Objectives of Neural Networks
- Biological Foundations of Neural Networks
- Early Neural Models
- Precursor to Current Models: Pattern Classification
- Resurgence of the Neural Network Approach
- Basic Concepts
- Classes of Neural Networks: Basic Network Properties
- Classification Models
- Association Models
- Optimization Models
- Self-Organization Models
- Radial Basis Functions (RBFs)
- Classification Networks and Learning: Network Structure
- Feature Selection
- Types of Learning
- Interpretation of Output
- Supervised Learning: Decision Surfaces
- Two-Category Separation
- Linearly Separable Sets
- Nonlinearly Separable Sets
- Multiple Category Classification Problems
- Relationship to Neural Network Models
- Comparison of Methods
- Unsupervised Learning: Background
- Kohonen Networks and Competitive Learning
- Hebbian Learning
- Adaptive Resonance Theory (ART)
- Design Issues: Input Data Types
- Structure of Networks
- Implications of Network Structures
- Choice of Learning Algorithm
- Comparative Analysis: Input Data Considerations
- Supervised Learning Algorithms
- Unsupervised Learning
- Network Structures
- Interpretation of Results
- Validation and Evaluation: Data Checking
- Validation of Learning Algorithm
Unit 2 ARTIFICIAL INTELLIGENCE Foundations of Computer-Assisted Decision Making
- Motivation for Computer-Assisted Decision Making
- Databases and Medical Records
- Mathematical Modeling and Simulation
- Pattern Recognition
- Bayesian Analysis
- Decision Theory
- Symbolic Reasoning Techniques
- Knowledge Representation: Production Rules
- Predicate Calculus and Semantic Nets
- Temporal Data Representations
- Knowledge Acquisition: Expert Input
- Learned Knowledge
- Knowledge Base Maintenance
- Reasoning Methodologies: Problem Representations
- Blind Searching
- Ordered Search
- AND/OR Trees
- Searching Game Trees
- Searching Graphs
- Rule Base Searching
- Higher-Level Reasoning Methodologies
- Examples in Biomedical Expert Systems
- Validation and Evaluation: Algorithmic Evaluation
- Knowledge Base Evaluation
- System Evaluation
Unit 3 ALTERNATIVE APPROACHES
- Genetic Algorithms: Foundations
- Representation Schemes
- Evaluation Functions
- Genetic Operators
- Evolution Strategies
- Biomedical Examples
- Probabilistic Systems: Bayesian Approaches
- Parameter Estimation
- Discriminant Analysis
- Statistical Pattern Classification
- Unsupervised Learning
- Regression Analysis
- Biomedical Applications
- Fuzzy Systems: Fuzzy Information
- Fuzzy Neural Networks
- Fuzzy Approaches for Supervised Learning Networks
- Fuzzy Generalizations of Unsupervised Learning Methods
- Reasoning with Uncertain Information
- Pre- Processing and Post-Processing Using Fuzzy Techniques
- Applications in Biomedical Engineering
- Hybrid Systems: Hybrid Systems Approaches
- Components of Hybrid Systems
- Use of Complex Data Structures
- Design Methodologies
Unit 4 HYBRID EXPERT SYSTEM
- Knowledge-Based Component: Crisp Implementation
- Partial Substantiation of Antecedents
- Weighted Antecedents and Partial Substantiation of Rules
- Handling of Temporal Data Neural Network Component: Learning Algorithm
- Special Data Types
- Analysis of Time Series Data: Chaos Theory
- Continuous versus Discrete Chaotic Modeling
- Difference Equations and Graphs
- Central Tendency Measure
- Combined System: Weighting of Antecedents
- Determination of Thresholds
- Neural Network with Symbolic Layer
- Application: Diagnosis of Heart Disease: Categories of Heart Disease
- Knowledge-Based Information
- Data-Based Information
- Chaotic Data
- Sample System
Unit 5 FUTURE PERSPECTIVES
- Effects of Hardware Advances: Faster Computing Speeds
- Increased Memory
- Parallel Machines
- Organic Semiconductors
- Effects of Increase in Knowledge: Information Explosion
- Human Genome Project
- Proliferation of Databases
- Communication of Information
- The Future of Software: Hybrid Systems
- Parallel Systems
- Non textual Data
- Neural Network Models
- Artificial Intelligence Approaches
Study on Android App:
