Fundamentals of Neural Networks
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 UpdatesGTU Previous Year Papers
Papers Coming Soon
We are working hard to add this material. Stay tuned for updates!
Follow on Instagram for UpdatesFundamentals of Neural Networks Syllabus — Unit-wise Content
The official GTU curriculum for Fundamentals of Neural Networks (subject code 3154601) as prescribed for AI & DS · Semester 5 divides the course into 6 units, covering 39 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 (3154601)Unit 1 INRODUCTION TO NEURAL NETWORKS
- History of development of neural network
- Biological neurons and artificial neurons
- Model of an ANN, Activation functions
- Classes of network architectures
- supervised and unsupervised learning rules
- Knowledge representation
- Neural Network applications
Unit 2 LEARNING IN NEURAL NETWORKS
- Vector and matrix algebra
- State-space concepts
- Concepts of optimization
- Error-correction learning
- Memory-based learning
- Hebbian learning
- Competitive learning
- Delta learning rule
- Windrow- Hoff learning rule
Unit 3 SINGLE LAYER PERCEPTRONS
- Structure of perceptron
- Learning in perceptron
- perceptron as classifier
- introduction and Bayes' classifiers
- Perceptron convergence
- Limitations of a perceptron
- Subject Code : 3154601 Subject Name : Fundamentals of Neural Networks
Unit 4 FEEDFORWARD NEURAL NETWORKS
- Feedforward ANN, Single layer feedforward network
- Multi-layer feedforward networks
- Working of Backpropagation algorithm
- Functional approximation with backpropagation
- Practical and design issues of backpropagation learning
Unit 5 SELF-ORGANIZING NETWORKS
- Two Basic Feature Mapping Models
- Self-Organization Map, SOM Algorithm
- Properties of Feature Map, Computer Simulations
- Learning Vector Quantization
- Adaptive Pattern Classification Korhonen algorithm
- Hopfield Networks: Hopfield network algorithm
- Adaptive resonance theory: Network and learning rules
Unit 6 ADVANCED NEURAL NETWORKS
- Radial Basis Functions
- Support Vector Machines
- Principle component Analysis
- Deep Learning
Study on Android App:
