AL-503 (C) RGPV B.Tech
Optimization Techniques in Machine Leaning (OTML)
Previous year papers and the official syllabus are free to read, no account needed.
Previous Year Papers
1 paper, latest Dec 2024
Syllabus, notes and important questions for AL-503 (C)
- Syllabus Official RGPV syllabus Free
- Notes 5 documents Free
- Important Questions None for AL-503 (C) yet
Syllabus units
Topics as the official RGPV syllabus lists them.
Unit 1 Introduction 5 topics
- What is optimization
- Formulation of LPP
- Solution of LPP: Simplex method
- Basic Calculus for optimization: Limits and multivariate functions
- Derivatives and linear approximations: Single‑variate functions and multivariate functions
Unit 2 Machine Learning Strategy 6 topics
- ML readiness
- Risk mitigation
- Experimental mindset
- Build / buy / partner
- Setting up a team
- Understanding and communicating change
Unit 3 Responsible Machine Learning 5 topics
- AI for good and all
- Positive feedback loops and negative feedback loops
- Metric design and observing behaviours
- Secondary effects of optimization
- Regulatory concerns
Unit 4 Machine Learning in Production and Planning 6 topics
- Integrating information systems
- Users break things
- Time and space complexity in production
- When to retain the model? Logging ML model versioning
- Knowledge transfer
- Reporting performance to stakeholders
Unit 5 Care and Feeding of Your Machine Learning Model 8 topics
- MLPL recap
- Post‑deployment challenges
- QUAM monitoring and logging
- QUAM testing
- QUAM maintenance
- QUAM updating
- Separating datastack from production
- Dashboard essentials and metrics monitoring
Exam insights
Counted from 4 past AL-503 (C) papers.
Marks asked per paper, by unit
-
Unit 1 Introduction 9 marks
-
Unit 2 Machine Learning Strategy 49 marks
-
Unit 3 Responsible Machine Learning 16 marks
-
Unit 4 Machine Learning in Production and Planning 35 marks
-
Unit 5 Care and Feeding of Your Machine Learning Model 12 marks
Average marks of the questions from each unit in one paper. You answer only some of them, so the total is more than the paper’s maximum.
Asked again and again
-
Explain the concept of batch normalization and its advantages in training deep neural networks.
Asked 2 times: 2024, 2022
-
Explain the backpropagation algorithm and how it updates the weights of a neural network.
Asked 2 times: 2024, 2023
-
Explain the working of Long Short‑Term Memory (LSTM) networks and their advantages over vanilla RNNs.
Asked 2 times: 2024, 2023