🧠
Module 1: AI Fundamentals
Types of AI, Machine Learning and Neural Networks
⏱️ Estimated reading time: 25 minutes
Chapter 1: Types of Artificial Intelligence
To pass, it is vital to distinguish between looking at the past and creating new content.
1. Predictive AI:
Uses historical data and statistical algorithms to identify patterns and predict future outcomes. It doesn't create anything new, just calculates probabilities.
*Example:* Lead Scoring, Sales Forecasting.
2. Generative AI (GenAI):
Uses Machine Learning algorithms to create new, original content (text, images, code) based on learned patterns.
*Example:* Drafting a personalized sales email, creating a marketing image.
3. Machine Learning (ML):
The engine behind AI. Main types:
- Supervised: We train the model with labeled data (e.g., photos of cats with the tag 'cat').
- Unsupervised: The model looks for patterns in unlabeled data by itself.
4. NLP (Natural Language Processing):
The branch of AI that allows machines to understand, interpret, and generate human language. It's what allows a Chatbot to understand you.
1. Predictive AI:
Uses historical data and statistical algorithms to identify patterns and predict future outcomes. It doesn't create anything new, just calculates probabilities.
*Example:* Lead Scoring, Sales Forecasting.
2. Generative AI (GenAI):
Uses Machine Learning algorithms to create new, original content (text, images, code) based on learned patterns.
*Example:* Drafting a personalized sales email, creating a marketing image.
3. Machine Learning (ML):
The engine behind AI. Main types:
- Supervised: We train the model with labeled data (e.g., photos of cats with the tag 'cat').
- Unsupervised: The model looks for patterns in unlabeled data by itself.
4. NLP (Natural Language Processing):
The branch of AI that allows machines to understand, interpret, and generate human language. It's what allows a Chatbot to understand you.
🎯 Key Points
- ✓ Predictive = Analyzes the past (Probability).
- ✓ Generative = Creates new content (Originality).
- ✓ NLP is the bridge between humans and machines.
- ✓ Machine Learning is the general field; Deep Learning is a more complex subfield.
Chapter 2: LLMs and Neural Networks
An LLM (Large Language Model) is a deep learning model trained on massive amounts of data to understand and generate text.
How does it work?
It doesn't 'know' things, it simply predicts the most likely next word (or token) in a sequence.
Key Concepts:
- Tokens: The basic unit of text for an LLM. Approximately 1 token = 0.75 words.
- Parameters: Internal variables the model adjusts during training. More parameters = greater reasoning capacity.
- Training: The process of feeding the model data so it learns patterns.
How does it work?
It doesn't 'know' things, it simply predicts the most likely next word (or token) in a sequence.
Key Concepts:
- Tokens: The basic unit of text for an LLM. Approximately 1 token = 0.75 words.
- Parameters: Internal variables the model adjusts during training. More parameters = greater reasoning capacity.
- Training: The process of feeding the model data so it learns patterns.
🎯 Key Points
- ✓ LLM predicts the next word based on probability.
- ✓ Tokenization is the process of converting text into numbers for AI.
- ✓ Deep Learning uses multi-layer neural networks (like the human brain).