Intended Audience
Network leadership, Planning, Engineering, and Operations
Objectives
After completing this course, the learner will be able to:
■ Define AI, Machine Learning, Deep Learning and evolution to Generative AI
■ Define Generative AI and list its benefits and challenges
■ Define the role of LLM and foundation models
■ Explain choices to augment foundation models and role of RAG
■ Walk-through sample use cases of Gen AI in telecom
■ List key challenges and future of Gen AI
Outline
1. Overview of AI, ML, and Generative AI
1.1 Introduction of AI and ML in Telecom
1.2 Evolution from AI to Generative AI
1.3 What and Why of GenAI
1.4 Discriminative AI vs. Generative AI
1.5 Key capabilities of Generative AI
1.6 Impact of Generative AI
1.7 Knowledge Check
2. Types of Generative AI Models
2.1 Large Language Models and Foundation Models
2.2 LLMs like GPT, Claude, Llama and Gemini
2.3 Prompt Engineering and GenAI
2.4 Zero-shot and Few-shot learning
2.5 Chain of Thought (CoT)
2.6 Knowledge Check
3. Customizing a Large Language Model (LLM)
3.1 Augmenting a LLM with Retrieval-Augmented Generation (RAG)
3.2 Refining a LLM with Fine Tuning
3.3 Web Grounding
3.4 LangChain and Prompt Chaining
3.5 Model Chaining
3.6 Knowledge Check
4. Gen AI Applications in Telecom
4.1 Optimization
4.2 Virtual Assistant
4.3 Fraud Detection and Security
4.4 Data Augmentation and Enhancement
4.5 Knowledge Check
5. Key Considerations of Gen AI
5.1 Challenges for implementing generative AI solutions
5.2 Data privacy and explainability
5.3 GenAI hallucinations
5.4 Model overfitting
5.5 Real-world uses of generative AI
5.6 Future of generative AI
5.7 Knowledge Check
