- ES Español (Latinoamérica)

- EN English

3.60. AI362 AI for edge computing (Elective)
- Credits: 3
- Hour of this course: Theory: 2 hours; Laboratory: 4 hours;
- Syllabus:


Español (Latinoamérica)

English - Prerrequisites:
- AI264 Deep Learning (7th Sem)
- ES Español (Latinoamérica)

- EN English

3.60.1. Justification Back to top


This course covers AI model deployment on edge devices (IoT, mobile, embedded), addressing optimization techniques, specialized frameworks, and privacy/security considerations in distributed systems.
- ES Español (Latinoamérica)

- EN English

3.60.2. Generales Goals Back to top


- Implement AI models optimized for edge hardware
- Design distributed inference pipelines
- Evaluate accuracy/latency/energy trade-offs
- ES Español (Latinoamérica)

- EN English

3.60.3. Contribution to Outcomes Back to top


- AG-C02) Ethics: Applies ethical principles and commits to professional ethics and the standards of professional computing practice. (Usage)
- AG-C09) Design and Development of Solutions: Designs, implements, and evaluates solutions for complex computing problems. (Assessment)
- AG-C12) Applies computer science theory and software development fundamentals to produce computer-based solutions. (Assessment)
- ES Español (Latinoamérica)

- EN English

3.60.4. Content Back to top


- ES Español (Latinoamérica)

- EN English

3.60.4.1. Edge AI Fundamentals (12 hours) [Skills AG-C09] Back to top


Bibliography: (Han and Lin, 2022)
Topics
- Hardware architectures for edge computing
- Edge-friendly model taxonomies (MobileNets, TinyML)
- Deployment frameworks (TF Lite, ONNX Runtime)
Learning Outcomes
- Select models matching hardware constraints [Assessment]
- Profile energy consumption on real devices [Usage]
- ES Español (Latinoamérica)

- EN English

3.60.4.2. Optimization Techniques (24 hours) [Skills AG-C09] Back to top


Bibliography: (Howard et al., 2017; Saraph and Warden, 2021)
Topics
- Quantization and pruning
- Knowledge distillation
- Specialized compilation (TVM, Apache MXNet)
Learning Outcomes
- Shrink models for microcontrollers [Assessment]
- Implement hybrid (edge+cloud) pipelines [Usage]
- ES Español (Latinoamérica)

- EN English

3.60.4.3. Security & Privacy (8 hours) [Skills AG-C09] Back to top


Bibliography: (Han and Lin, 2022)
Topics
- Federated learning at edge
- Homomorphic encryption
- Edge model attacks (adversarial examples)
Learning Outcomes
- Analyze edge system vulnerabilities [Familiarity]
- Implement basic defenses [Usage]
- ES Español (Latinoamérica)

- EN English

3.60.5. Bibliography Back to top


Han, S. and Lin, Y. (2022). Edge AI: Systems Design for Embedded Machine Learning. Springer.
Howard, A., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv:1704.04861.
Saraph, V. and Warden, P. (2021). Tinyml: Enabling always-on ml on the edge. In ACM HotNets.