From Coin Toss to LLM — Understanding Random Variables
A beginner-friendly guide to probability and random variables, covering concepts like coin tosses, dice rolls, and how large language models (LLMs) work.
Why it matters
Understanding random variables and probability is crucial for working with machine learning and AI systems, which often rely on probabilistic models and predictions.
Key Points
- 1Probability is a number between 0 and 1 that measures how likely something is to happen
- 2A random variable is an empty slot that gets filled with a number after an experiment is run
- 3Random variables can be discrete (only specific countable values) or continuous (any value in a range)
- 4Examples of random variables include coin tosses, dice rolls, and the next word prediction by an LLM
Details
The article explains the basics of probability, starting with a simple coin toss example. It then introduces the concept of a random variable, which is an empty slot that gets filled with a number after an experiment is run. Random variables can be either discrete (only specific countable values) or continuous (any value in a range). The article walks through examples of discrete random variables like coin tosses and dice rolls, as well as a more complex example of an LLM predicting the next word in a sentence. The LLM has a fixed vocabulary and assigns probabilities to each possible next word based on its internal calculations.
No comments yet
Be the first to comment