- ES Español (Latinoamérica)

- EN English

2.8. Artificial Intelligence Mathematics (AIM)
This area covers the advanced mathematical foundations of modern artificial intelligence, with emphasis on deep learning theory, advanced neural architectures, reinforcement learning, and generative models. It provides the theoretical understanding needed to develop novel AI architectures, analyze their properties, and understand their limitations. The focus is on the mathematical principles that enable machines to learn complex representations and make intelligent decisions.
| Knowledge Area (KA) | Core Tier1 | Core Tier2 |
2.8.1 Deep Learning Theory | 1 | 1 |
2.8.2 Advanced Neural Architectures | 1 | 1 |
2.8.3 Reinforcement Learning | 1 | 1 |
2.8.4 Natural Language Processing with Transformers | 1 | 1 |
2.8.5 Generative Models and GANs | 1 | 1 |
2.8.1. AIM/Deep Learning Theory (Core Tier1: 1 hr, Core Tier2: 1 hr) ↑ Back to top
Topics:
Core
- Universal approximation theorems
- Optimization landscape of deep networks
- Generalization in deep learning
- Representation learning theory
- Training dynamics and gradient flow
Learning Outcomes:
Core:
- Explain universal approximation theorems and their implications [Familiarity]
- Analyze the optimization landscape of deep networks [Assessment]
- Study generalization phenomena in deep learning [Assessment]
- Analyze training dynamics of neural networks [Assessment]
2.8.2. AIM/Advanced Neural Architectures (Core Tier1: 1 hr, Core Tier2: 1 hr) ↑ Back to top
Topics:
Core
- Convolutional Neural Networks (CNNs)
- Recurrent Neural Networks (RNNs) and LSTMs
- Transformer architectures
- Attention mechanisms
- Graph Neural Networks (GNNs)
Learning Outcomes:
Core:
- Design CNN architectures for visual tasks [Usage]
- Implement RNNs for sequence modeling [Usage]
- Apply transformer architectures to various domains [Usage]
- Use attention mechanisms in neural networks [Usage]
2.8.3. AIM/Reinforcement Learning (Core Tier1: 1 hr, Core Tier2: 1 hr) ↑ Back to top
Topics:
Core
- Markov Decision Processes (MDPs)
- Value iteration and policy iteration
- Q-learning and temporal difference learning
- Policy gradient methods
- Deep reinforcement learning
Learning Outcomes:
Core:
- Formulate problems as Markov Decision Processes [Usage]
- Implement value and policy iteration [Usage]
- Apply Q-learning for model-free RL [Usage]
- Use policy gradient methods [Usage]
2.8.4. AIM/Natural Language Processing with Transformers (Core Tier1: 1 hr, Core Tier2: 1 hr) ↑ Back to top
Topics:
Core
- Transformer architecture and self-attention
- BERT and pre-trained language models
- GPT models and autoregressive generation
- Multimodal transformers
- Efficient transformer variants
Learning Outcomes:
Core:
- Implement transformer models from scratch [Usage]
- Fine-tune pre-trained language models [Usage]
- Apply GPT models for text generation [Usage]
- Use multimodal transformers for cross-modal tasks [Usage]
2.8.5. AIM/Generative Models and GANs (Core Tier1: 1 hr, Core Tier2: 1 hr) ↑ Back to top
Topics:
Core
- Generative Adversarial Networks (GANs)
- Variational Autoencoders (VAEs)
- Normalizing flows
- Diffusion models
- Evaluation of generative models
Learning Outcomes:
Core:
- Implement GANs for image generation [Usage]
- Apply VAEs for latent representation learning [Usage]
- Use diffusion models for generation [Usage]
- Evaluate generative model quality [Assessment]