Scribd
Upload
29 views2 pages

Edwin Edwin Sanga AI

The document discusses three main categories of learning in artificial intelligence: supervised learning, unsupervised learning, and reinforcement learning. Supervised learning uses labeled input and output data to make predictions on new data. Unsupervised learning finds patterns in unlabeled input data through clustering. Reinforcement learning interacts with an environment and receives rewards or punishments to learn a policy that maximizes cumulative reward over time.

Uploaded by

Edwin Sanga
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
29 views2 pages

Edwin Edwin Sanga AI

The document discusses three main categories of learning in artificial intelligence: supervised learning, unsupervised learning, and reinforcement learning. Supervised learning uses labeled input and output data to make predictions on new data. Unsupervised learning finds patterns in unlabeled input data through clustering. Reinforcement learning interacts with an environment and receives rewards or punishments to learn a policy that maximizes cumulative reward over time.

Uploaded by

Edwin Sanga
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

DAR ES SALAAM INSTITUTE OF TECHNOLOGY

COMPUTER STUDIES DEPARTMENT

ORDINARY DIPLOMA IN COMPUTER ENGINEERING

ARTIFICIAL INTELLIGENCE

INDIVIDUAL ASSIGNMENT NO. 1

NAME: EDWIN EDWIN SANGA


Reg No: 2002202210708
OD20-C0E
1. Explains unsupervised , supervised and reinforcement as in artificial
intelligence
There are three main categories of learning: supervised learning, unsupervised learning, and
reinforcement learning.

1. Supervised Learning: Supervised learning is a type of machine learning where an


algorithm is trained on labeled data. In supervised learning, the algorithm is given input
data and corresponding output data, and it learns to map the input to the output. The
goal of supervised learning is to make accurate predictions for new, unseen data.

For example, in an image classification task, the algorithm is given a set of labeled images and
learns to recognize patterns in the images that correspond to different categories, such as
"dog," "cat," or "bird." Once the algorithm has learned to recognize these patterns, it can be
used to classify new, unseen images.

2. Unsupervised Learning: Unsupervised learning is a type of machine learning where the


algorithm is not given labeled data. Instead, the algorithm is given a set of input data
and must find patterns or relationships within the data. The goal of unsupervised
learning is to discover hidden structures or relationships in the data.

For example, in a clustering task, the algorithm is given a set of data points and must group
them into clusters based on their similarities. The algorithm does not know beforehand what
the clusters should be, but must instead discover them based on the similarities between the
data points.

3. Reinforcement Learning: Reinforcement learning is a type of machine learning where


the algorithm learns by interacting with an environment. The algorithm is given a set of
actions it can take in the environment, and it receives feedback in the form of rewards
or punishments based on the actions it takes. The goal of reinforcement learning is to
learn a policy that maximizes the cumulative reward over time.

For example, in a game-playing task, the algorithm is given a set of possible moves it can make
and must learn to make the moves that result in the highest score. The algorithm receives
feedback in the form of a score after each move, and it adjusts its policy based on this feedback
to try to maximize its score over time.

You might also like