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
- What is generative AI?
- Generative AI compared to other AI types
- Overview of primary techniques and models in generative AI
- Applications and use cases of generative AI
- Challenges and limitations of generative AI
Creating Images with Generative AI
- Generating images from textual descriptions
- Utilizing GANs to produce realistic and diverse images
- Employing VAEs to create images with latent variables
- Applying artistic styles to images via style transfer
Creating Text with Generative AI
- Generating text from text prompts
- Using transformer-based models to create contextually coherent text
- Performing text summarization to condense lengthy texts
- Using text paraphrasing to express the same meaning in different ways
Creating Audio with Generative AI
- Generating speech from text
- Transcribing speech to text
- Composing music from text or audio inputs
- Generating speech with specific voice characteristics
Creating Other Content with Generative AI
- Generating code from natural language descriptions
- Producing product sketches from text descriptions
- Creating video content from text or images
- Generating 3D models from text or images
Evaluating Generative AI
- Assessing content quality and diversity in generative AI outputs
- Applying metrics such as Inception Score, Fréchet Inception Distance, and BLEU score
- Conducting human evaluation through crowdsourcing and surveys
- Implementing adversarial evaluation methods, including Turing tests and discriminators
Understanding Ethical and Social Implications of Generative AI
- Ensuring fairness and accountability
- Preventing misuse and abuse
- Respecting the rights and privacy of content creators and consumers
- Promoting creativity and collaboration between humans and AI
Summary and Next Steps
Requirements
- Understanding of fundamental AI concepts and terminology.
- Experience with Python programming and data analysis.
- Familiarity with deep learning frameworks like TensorFlow or PyTorch.
Audience
- Data scientists.
- AI developers.
- AI enthusiasts.
14 Hours
Testimonials (2)
The interactive style, the exercises
Tamas Tutuntzisz
Course - Introduction to Prompt Engineering
A great repository of resources for future use, instructor's style (full of good sense of humor, great level of detail)
