Duration
2 days
Course Description
This course provides an overview into the world of generative artificial intelligence (AI) and the use of various generative models in numerous use cases. As a participant, you'll explore the key concepts, techniques, and best practices involved in working with generative models such as GAN, CLIP, Stable Diffusion, ChatGPT, and Bard.
Module 1: Exploring Generative AI
- Deep Learning Models
- Discriminative vs. Generative AI
- Why does Generative AI matter?
- Content Creation using generative AI
Module 2: Exploring Generative Adversarial Networks Approach and Techniques
- Image Generation Applications
- Understanding GAN Architectures
- Data Augmentation with a GAN
- Conditional GAN (cGAN)
- 3D-Object Generation
- Style GAN for face generation
- Fine Tuning GAN for your custom tasks
Module 3: Contrastive Language-Image Pretraining (CLIP) Approach and Techniques
- From GANs to CLIP
- Image To Text Applications
- CLIP Architecture
- Converting image to Text using CLIP
- Fine Tuning CLIP for your custom tasks
Module 4: Exploring Stable Diffusion Approach and Techniques
- Text-to-Image Applications
- Image-to-Image Applications
- Stable Diffusion Architecture
- Stable Diffusion for Text-to-Image generation
- Data Augmentation with Stable Diffusion
- Stable Diffusion for face generation
- Fine Tuning Stable Diffusion for your custom tasks
Module 5: Generative Language Models
- Applications of Natural Language Models in Generative AI
- Explore Generative LLMs (Large Language Models)
- Explore Google Bard: Features & Capabilities
- Explore ChatGPT: Features & Capabilities
- Prompt Engineering for Effective AI Interactions
- Fine Tuning generative models
Module 6: Ethical Consideration in Generative AI
- Ethical and Proficiency Requirements for Proficient Work in Generative AI
- Reevaluating AI Bias & Human Centrality in Technology
- Responsible AI Practices & Mitigating Risks
Programme scope, delivery arrangements and suitability are confirmed during enquiry.