Get in Touch

Course Outline

Introduction to Generative AI

  • Defining generative AI and its significance.
  • Overview of primary types and techniques in generative AI.
  • Key challenges and limitations of generative AI.

Transformer Architecture and LLMs

  • Understanding the transformer model and its operation.
  • Core components and features of transformers.
  • Leveraging transformers to build LLMs.

Scaling Laws and Optimization

  • The importance of scaling laws for LLMs.
  • The relationship between scaling laws, model size, data volume, compute budget, and inference needs.
  • Applying scaling laws to enhance LLM performance and efficiency.

Training and Fine-Tuning LLMs

  • Primary steps and challenges in training LLMs from scratch.
  • Advantages and disadvantages of fine-tuning LLMs for specialized tasks.
  • Best practices and tools for training and fine-tuning LLMs.

Deploying and Using LLMs

  • Key considerations and challenges of production deployment.
  • Common use cases and applications of LLMs across various industries.
  • Integrating LLMs with other AI systems and platforms.

Ethics and Future of Generative AI

  • Ethical and social implications of generative AI and LLMs.
  • Potential risks and harms, such as bias, misinformation, and manipulation.
  • Principles for the responsible and beneficial use of generative AI.

Summary and Next Steps

Requirements

  • Understanding of machine learning fundamentals, including supervised and unsupervised learning, loss functions, and data splitting techniques.
  • Proficiency in Python programming and data manipulation.
  • Foundational knowledge of neural networks and natural language processing (NLP).

Target Audience

  • Software developers
  • Machine learning enthusiasts
 21 Hours

Number of participants


Price per participant

Testimonials (7)

Upcoming Courses

Related Categories