Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Duration 21 hours
Course Outline
Introduction to LLMs and Generative AI
- Reviewing key techniques and model architectures
- Examining real-world applications and use cases
- Identifying current challenges and limitations
Applying LLMs to NLU Tasks
- Sentiment analysis
- Named entity recognition
- Relation extraction
- Semantic parsing
Applying LLMs to NLI Tasks
- Detecting entailment
- Detecting contradictions
- Identifying paraphrases
Using LLMs for Knowledge Graphs
- Extracting facts and relationships from text
- Inferring missing or new facts
- Leveraging knowledge graphs for downstream tasks
Utilizing LLMs for Commonsense Reasoning
- Generating plausible explanations, hypotheses, and scenarios
- Incorporating commonsense knowledge bases and datasets
- Evaluating reasoning capabilities
LLM-Driven Dialogue Generation
- Creating interactions for chatbots, virtual assistants, and conversational agents
- Dialogue management strategies
- Utilizing dialogue datasets and evaluation metrics
LLMs for Multimodal Generation
- Image generation from text
- Text generation from images
- Video generation from text or images
- Audio generation from text
- Text generation from audio
- 3D model generation from text or images
LLMs in Meta-Learning
- Adapting LLMs to new domains, tasks, or languages
- Learning from few-shot or zero-shot examples
- Applying meta-learning and transfer learning frameworks
LLMs and Adversarial Learning
- Defending against malicious attacks
- Detecting and mitigating biases and errors
- Using robustness datasets and adversarial methods
Evaluating LLMs and Generative AI
- Measuring content quality and diversity
- Using metrics such as inception score, Fréchet inception distance, and BLEU
- Employing human evaluation methods like crowdsourcing and surveys
- Applying adversarial evaluation techniques like Turing tests
Ethical Principles for LLMs and Generative AI
- Ensuring fairness and accountability
- Preventing misuse and abuse
- Protecting the rights and privacy of creators and consumers
- Encouraging human-AI collaboration and creativity
Summary and Next Steps
Requirements
- Foundational knowledge of AI concepts and terminology
- Practical experience with Python programming and data analysis
- Proficiency with deep learning frameworks like TensorFlow or PyTorch
- Basic understanding of LLM architectures and their applications
Target Audience
- Data scientists
- AI developers
- AI enthusiasts
