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 Generative Artificial Intelligence
- Definition and scope of Generative AI
- Historical development and technological evolution of Generative AI
- Essential terminology and core concepts
Fundamentals of Machine Learning
- Overview of machine learning principles
- Categorization of learning paradigms: Supervised, Unsupervised, and Reinforcement
- Foundational algorithms and modeling techniques
- Data preparation strategies and feature engineering
Deep Learning Foundations
- Neural network architectures and deep learning principles
- Mechanisms of activation functions, loss functions, and optimization algorithms
- Strategies for mitigating overfitting, underfitting, and regularization
- Familiarization with TensorFlow and PyTorch frameworks
Overview of Generative Modeling
- Distinctions between discriminative and generative modeling approaches
- Operational use cases for generative models
Variational Autoencoders (VAEs)
- Principles of autoencoder architectures
- Structural components of VAEs
- The role and importance of latent space representation
- Practical exercise: Development of a basic VAE model
Generative Adversarial Networks (GANs)
- Fundamental concepts of GANs
- Architectural design involving Generator and Discriminator components
- Practical exercise: Implementation of a basic GAN
Advanced Generative Architectures
- Introduction to Transformer-based models
- Practical exercise: Text synthesis utilizing pre-trained GPT models
Ethical Frameworks and Governance Implications
- Addressing bias and ensuring fairness in AI model outputs
- Forward-looking implications and standards for responsible AI adoption
Sectoral Applications of Generative AI
- Integration of Generative AI in scientific research and discovery
Comprehensive Capstone Project
- Conceptualization and proposal development for a Generative AI initiative
- Curation, collection, and preprocessing of project datasets
- Assessment of model performance and formal presentation of findings
Synthesis and Future Trajectory
Requirements
- Proficiency in fundamental programming constructs using Python
- Competence in core mathematical disciplines, with specific emphasis on probability theory and linear algebra
Target Audience
- Technical developers and IT specialists within government agencies
14 Hours
Testimonials (2)
the tips and recommended prompts that we can take away from this training
Lee Mei Lin - ST Engineering IHQ Pte Ltd
Course - InVideo AI: Creating Engaging Short-Form Videos
use of proper and effective prompt
