Aylin’s AI Learning Map

Hands-on, curiosity-driven AI exploration with tasks, links, and key takeaways

Hello! My name is Aylin Muzaffarli, I’m 14 years old, from Azerbaijan.
Here, I share AI resources, tasks, and insights that have truly helped me learn.

I’ve tried several AI courses — they were interesting, but long 2–3 hour lectures didn’t fit my learning style. That’s why I decided to create my own syllabus, focusing on essential topics with carefully chosen resources and practical tasks.

Here, you’ll find my AI learning map and the key lessons and takeaways from each topic that I’ve found most useful so far.

If you’re new to AI, I recommend starting with Elements of AI – Introduction to AI (p.1).
After that, you can explore Elements of AI – Building AI (p.2).

More about me

Email: muzaffaraylin@gmail.com

Socials & contact: Contact me

Table of Contents

Neural Networks (NNs)

Key Takeaways

A neural network is a function that learns patterns from data by passing inputs through layers of simple units called “neurons.” Each layer transforms the data, and learning adjusts these transformations to make better predictions. Think of it as a machine gradually figuring out which features matter most.

Goal

Understand neurons, layers, activation, and training.

Task (Practice)

Links / Resources

Embeddings

Key Takeaways

Embeddings convert words, sentences, or images into numerical vectors in a multi-dimensional space, enabling AI models to capture semantic relationships. This transformation allows AI to understand and compare meanings effectively.

Goal

Learn how text/images are converted into vectors for AI models.

Task (Practice)

Links / Resources

Transformers & Large Language Models (LLMs)

Key Takeaways

Transformers are the backbone of modern AI models, including large language models (LLMs) like GPT. Their core idea is attention, which allows the model to focus on the most relevant parts of input data simultaneously. This enables them to handle large datasets and complex tasks efficiently. LLMs are simply transformers specialized for understanding and generating text.

Goal

Understand the basics of transformers and LLMs.

Task (Practice)

Links / Resources

Computer Vision (CV)

Key Takeaways

Computer Vision (CV) enables AI to interpret and understand images or video. Models learn patterns in pixels to recognize objects, detect features, and make predictions. Essentially, it teaches machines to “see” and make sense of visual data.

Goal

Understand the basics of how computers process and interpret images.

Task (Practice)

Links / Resources

Generative Models

Key Takeaways

Generative models are AI systems that can create new content, such as text, images, or music, based on patterns they learned from training data. Large language models (LLMs) like GPT generate text, while models like DALL·E or Stable Diffusion generate images. The core idea is that the model learns the underlying structure of data and can produce new, meaningful outputs.

Goal

Understand the basics of how generative models work and see them in action.

Task (Practice)

Links / Resources

Reinforcement Learning (RL)

Key Takeaways

Reinforcement Learning is a type of machine learning where an agent learns to make decisions by interacting with an environment and receiving feedback in the form of rewards. It's widely used in AI for games, robotics, and decision-making systems.

Goal

Understand the basics of RL and its core concepts: agent, environment, states, actions, rewards, and policies.

Task (Practice)

Think of a simple scenario, like a game or moving an agent on a small grid. Ask yourself: what actions would maximize rewards? How would the agent learn from trial and error? This helps you understand RL conceptually without coding.

Links / Resources

Ethics, Bias, and Fairness

Key Takeaways

AI systems can unintentionally reflect or amplify human biases in data. Understanding ethics and fairness helps ensure AI is responsible, safe, and inclusive.

Goal

Learn why ethical considerations, bias detection, and fairness matter in AI development.

Task (Practice)

Examine a dataset or AI output. Ask: Are some groups underrepresented or misrepresented? What biases could appear? Think of ways to reduce them.

Links / Resources

Production ML / Deployment

Key Takeaways

After building AI models, deploying them in real-world applications requires careful planning: scaling, monitoring, and maintenance are essential for reliable performance.

Goal

Understand the basics of deploying ML models, monitoring performance, and integrating AI into applications.

Task (Practice)

Explore a pre-trained model on Hugging Face or Kaggle and try running it in a simple web app or notebook. Observe how inputs lead to outputs and think about how it could be integrated into a real-world system.

Links / Resources