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.
Course Outline
Introduction to LLMs and Generative AI
- Exploring relevant techniques and models
- Discussing key applications and use cases
- Identifying inherent challenges and limitations
Leveraging LLMs for NLU Tasks
- Sentiment analysis
- Named entity recognition
- Relation extraction
- Semantic parsing
Leveraging LLMs for NLI Tasks
- Entailment detection
- Contradiction detection
- Paraphrase detection
Utilizing LLMs for Knowledge Graphs
- Extracting facts and relations from text
- Inferring missing or new facts
- Applying knowledge graphs to downstream tasks
Leveraging LLMs for Commonsense Reasoning
- Generating plausible explanations, hypotheses, and scenarios
- Using commonsense knowledge bases and datasets
- Evaluating commonsense reasoning capabilities
Generating Dialogue with LLMs
- Creating interactions with conversational agents, chatbots, and virtual assistants
- Managing dialogue flows
- Utilizing dialogue datasets and performance metrics
Multimodal Generation with LLMs
- Generating images from text
- Generating text from images
- Creating videos from text or images
- Synthesizing audio from text
- Generating text from audio
- Creating 3D models from text or images
Meta-Learning with LLMs
- Adapting LLMs to new domains, tasks, or languages
- Learning from few-shot or zero-shot examples
- Employing meta-learning and transfer learning datasets and frameworks
Adversarial Learning with LLMs
- Protecting LLMs against malicious attacks
- Detecting and mitigating biases and errors
- Using adversarial learning and robustness datasets and methods
Evaluating LLMs and Generative AI
- Assessing content quality and diversity
- Applying metrics such as inception score, Fréchet inception distance, and BLEU score
- Using human evaluation methods like crowdsourcing and surveys
- Employing adversarial evaluation methods like Turing tests and discriminators
Ethical Principles for LLMs and Generative AI
- Ensuring fairness and accountability
- Preventing misuse and abuse
- Respecting the rights and privacy of content creators and consumers
- Fostering creativity and collaboration between humans and AI
Summary and Next Steps
Requirements
- Familiarity with fundamental AI concepts and terminology
- Practical experience with Python programming and data analysis
- Knowledge of deep learning frameworks such as TensorFlow or PyTorch
- Basic understanding of LLMs and their practical applications
Target Audience
- Data scientists
- AI developers
- AI enthusiasts
21 Hours