Optimization
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 UpdatesOptimization Syllabus — Unit-wise Content
The official GTU curriculum for Optimization (subject code ME01095071) as prescribed for AIAD · Semester 1 divides the course into 5 units, covering 35 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 (ME01095071)Unit 1 Introduction to Optimization
- Definition of optimization
- types of problems (linear
- optimization vs. machine learning vs. search algorithms. optimization in reinforcement learning
- optimization in natural language processing Program Name: Master of Engineering Level: PG Branch: Computer Engineering (Artificial Intelligence And Data Science) Course / Subject Code : ME01095071 Subject Name: Optimization
Unit 2 Unconstrained & Constrained Optimization
- Gradient descent methods (batch
- Newton's method and variants
- convergence analysis
- stochastic gradient descent
- Lagrange multipliers
- Karush-Kuhn-Tucker (KKT) conditions
- penalty methods
- interior point methods Metaheuristic Optimization Techniques: Genetic algorithms (encoding
- particle swarm optimization
- ant colony optimization
- simulated annealing
Unit 3 Evolutionary Algorithms and Optimization in Machine Learning
- Evolutionary strategies
- genetic programming
- differential evolution
- Optimization in neural networks (backpropagation
- stochastic gradient descent
- Adam optimizer)
- support vector machines (dual and primal optimization) Feature selection
- dimensionality reduction (PCA
- hyperparameter tuning (grid search
- Bayesian optimization)
Unit 4 Ethical consideration for Optimization
- Optimization for interpretable AI, fairness and bias reduction in optimization
- optimization in federated learning
- Bias and fairness issues in optimization algorithms
- ethical implications of optimization in AI and data science
Unit 5 Optimization applications and case studies in data science
- Resource Allocation
- Recommendation Systems
- Energy Optimization
- Route Optimization
- Supply chain Optimization
- Case Studies : Netflix
Study on Android App:
