Page 180 - AI Computer 10

Pop Quiz Quiz
Pop
Identify the model: Supervised or Unsupervised?
a. A model using social media platforms to recognise your friends in a picture from a collection of
tagged photos.
___________________________________________________________________________________________
b. An online store groups customers based on shopping behavior without predefined labels.
___________________________________________________________________________________________
c. A model trained using labeled X-ray images where doctors have marked "Healthy" or "Diseased"
patients.
___________________________________________________________________________________________
d. A model trained on labeled images of handwritten numbers (0-9) to classify new digits.
___________________________________________________________________________________________
e. A model is trained on past sales data (date, revenue) to predict future sales.
___________________________________________________________________________________________

f. A model clusters news articles into groups based on content similarity without predefined categories.
___________________________________________________________________________________________

Reinforcement Learning

Reinforcement learning refers to the process of training the machine learning models to make a sequence of
decisions. In reinforcement learning, machines learn how to achieve a goal in an uncertain, potentially complex
environment.

Unlike supervised learning, where the model learns from labeled data, reinforcement learning involves an agent
that learns by interacting with its environment and receiving feedback in the form of rewards or penalties. A
great example of reinforcement learning is autonomous vehicles where driving decisions are based on changing
environments and road conditions.

State Action

Rewards
Driving Environment Vehicle Control
Safe
Efficient
Comfortable
There are aspects of Reinforcement Learning, notably distinct from Supervised and Unsupervised Learning. Let
us understand these.
1. Data is gathered by the AI agent itself during its interaction with the environment and perceiving stated
changes. For example, an AI agent playing a digital game of chess makes moves and perceives changes in the
board based on its moves.
2. The rewards are input data received by the agent when certain criteria are satisfied. For example, the AI
agent in chess will make many moves before each win or loss. These criteria are typically unknown to the
agent at the outset of training.

46
46