<aside>

Basic Definitions & Key Concepts in AI

<aside>

Artificial Intelligence (AI)

The field of computer science focused on creating systems that can perform tasks that typically require human intelligence—like reasoning, learning, problem-solving, or understanding language.

</aside>

<aside>

Machine Learning (ML)

A subset of AI where algorithms learn from data to improve performance over time without being explicitly programmed. It powers most modern AI systems.

</aside>

<aside>

Deep Learning

A type of machine learning based on neural networks with many layers (hence “deep”). Used for tasks like image recognition, language modeling, and speech processing.

</aside>

<aside>

Neural Network

A system of interconnected nodes (neurons) modeled after the human brain. It processes input data and adjusts connections (weights) based on feedback to improve output accuracy.

</aside>

<aside>

Model

An AI model is a trained system that can make predictions or generate outputs based on input data. [Examples: GPT, DALL·E, Stable Diffusion.]

</aside>

<aside>

Training

The process of feeding large amounts of data into a model and adjusting its parameters so it learns patterns and relationships.

</aside>

<aside>

Inference

The use of a trained model to generate predictions, answers, or outputs when given new inputs. For example, ChatGPT replying to your question is inference.

</aside>

<aside>

Prompt

An input or instruction given to an AI model to generate a desired output. Crafting prompts effectively is called prompt engineering.

</aside>

<aside>

Large Language Model (LLM)

A type of AI model trained on vast text datasets to understand and generate human-like language. Example: OpenAI’s GPT models.

</aside>

<aside>

Parameters

These are the internal numbers in a model. More parameters often mean more complex and capable models.

</aside>

<aside>

Token

A chunk of text used by language models.

</aside>

<aside>

Fine-Tuning

Customizing a pre-trained model on specific data to specialize it for a particular task or domain.

</aside>

<aside>

Bias

AI models can reflect or amplify biases present in training data. It's important to evaluate AI output critically and ethically.

</aside>

<aside>

Overfitting

When a model learns the training data too well, including its noise or errors, and performs poorly on new data.

</aside>

</aside>

<aside>

✅Topic Completed!

🌟Great work! You’re one step closer to your goal.

Ready to Move On →

</aside>

<aside>