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
- Examining various techniques and models
- Reviewing real-world applications and scenarios
- Recognizing potential challenges and constraints
Applying LLMs to NLU Tasks
- Sentiment analysis
- Named entity recognition
- Relation extraction
- Semantic parsing
Applying LLMs to NLI Tasks
- Identifying entailment
- Detecting contradictions
- Recognizing paraphrases
Utilizing LLMs for Knowledge Graphs
- Extracting facts and relationships from text
- Inferring missing or new information
- Leveraging knowledge graphs for subsequent tasks
Applying LLMs to Commonsense Reasoning
- Generating plausible explanations, hypotheses, and scenarios
- Leveraging commonsense knowledge bases and datasets
- Assessing the quality of commonsense reasoning
Applying LLMs to Dialogue Generation
- Creating dialogues for conversational agents, chatbots, and virtual assistants
- Managing dialogue flows
- Utilizing dialogue datasets and performance metrics
Applying LLMs to Multimodal Generation
- Creating images from text descriptions
- Generating text descriptions from images
- Producing videos from text or image inputs
- Generating audio from text
- Creating text from audio inputs
- Generating 3D models from text or images
Applying LLMs to Meta-Learning
- Adapting LLMs for new domains, tasks, or languages
- Learning from limited or no examples
- Using meta-learning and transfer learning resources and frameworks
Applying LLMs to Adversarial Learning
- Protecting LLMs from malicious attacks
- Identifying and reducing biases and errors in LLMs
- Employing adversarial learning and robustness datasets and methods
Evaluating LLMs and Generative AI
- Measuring content quality and diversity
- Utilizing metrics such as inception score, Fréchet inception distance, and BLEU score
- Employing human evaluation techniques like crowdsourcing and surveys
- Using adversarial evaluation methods such as Turing tests and discriminators
Applying Ethical Principles to LLMs and Generative AI
- Ensuring fairness and accountability
- Preventing misuse and abuse
- Safeguarding the rights and privacy of content creators and users
- Promoting creativity and collaboration between humans and AI
Summary and Next Steps
Requirements
- A grasp of fundamental AI principles and terminology
- Proficiency in Python programming and data analysis
- Familiarity with deep learning frameworks like TensorFlow or PyTorch
- A basic understanding of LLMs and their practical applications
Intended Audience
- Data scientists
- AI developers
- AI enthusiasts
