Artificial 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 UpdatesArtificial Neural Networks Syllabus — Unit-wise Content
The official GTU curriculum for Artificial Neural Networks (subject code 2730503) as prescribed for EAC( · Semester 3 divides the course into 5 units, covering 31 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 (2730503)Unit 1 Introduction to ANN
- structure and working of Biological Neural Network
- Trends in Computing Comparison of BNN and ANN
Unit 2 Basics of Artificial Neural Networks -
- History of neural network research
- characteristics of neural networks terminology
- models of neuron Mc Culloch – Pitts model
- Adaline model
- Basic learning laws
- Topology of neural network architecture
Unit 3 Backpropagation networks
- (BPN) Architecture of feed forward network
- single layer ANN, multilayer perceptron
- back propagation learning
- input - hidden and output layer computation
- backpropagation algorithm
- selection of tuning parameters in BPN, Numbers of hidden nodes
Unit 4 Activation & Synaptic Dynamics
- Activation Dynamics models
- synaptic Dynamics models
- stability and convergence
- recall in neural networks
Unit 5 Basic functional units of ANN for pattern recognition tasks
- Basic feed forward
- Basic feedback and basic competitive learning neural network. 4 9 Pattern association
- pattern classification and pattern mapping tasks. 6 a) Feedforward neural networks – - Linear responsibility X-OR problem and solution. - Analysis of pattern mapping networks summary of basic gradient search methods. b) Feed back neural networks Pattern storage networks
- stochastic networks and simulated annealing
- Boltzmann machine and Boltzmann learning 6 14 7 Competitive learning neural networks : Components of CL network pattern clustering and feature mapping network
- ART networks
- Features of ART models
- character recognition using ART network. 6 14 8 Applications of ANN : Pattern classification – Recognition of Olympic games symbols
- Recognition of printed Characters
- Neocognitron – Recognition of handwritten characters
- NET Talk: to convert English text to speech
- Recognition of consonant vowel (CV) segments
- texture classification and segmentation
Study on Android App:
