Scribd
Upload
10 views

Machine Learning

Machine learning involves both supervised and unsupervised learning techniques: supervised learning uses labeled training data to learn relationships and make predictions, while unsupervised learning discovers hidden patterns in unlabeled data. Reinforcement learning differs in that an agent learns from trial-and-error interactions with a dynamic environment by discovering actions that maximize rewards. The document outlines different machine learning algorithms for these three main categories of machine learning.

Uploaded by

Rajveer Jain
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
10 views

Machine Learning

Machine learning involves both supervised and unsupervised learning techniques: supervised learning uses labeled training data to learn relationships and make predictions, while unsupervised learning discovers hidden patterns in unlabeled data. Reinforcement learning differs in that an agent learns from trial-and-error interactions with a dynamic environment by discovering actions that maximize rewards. The document outlines different machine learning algorithms for these three main categories of machine learning.

Uploaded by

Rajveer Jain
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 21

Machine Learning

Piyush Dave
Machine Learning is the science (and art) of
programming computers so they can learn from data.

Reference:- Hands-On Machine Learning with Scikit-Learn and TensorFlow 2nd Edition by Aurélien Géron
In supervised learning, the training data you
feed to the algorithm includes the
desiredsolutions, called labels
Ham labeled training set for supervised
learning Instance
Spam
Ham

Spam

Machine
Ham Spam
Is

Learning
Ham

Spam

Ham
Types of Supervise Learning

Decision Trees
k-Nearest Logistic Support Vector
Linear Regression and Random
Neighbors Regression Machines (SVMs)
Forests
In unsupervised learning, as you might guess,
the training data is unlabeled. The system tries
to learn without a teacher.
1. Machine Extract
Feature from
Data

2. Based on
Feature, Data
will be separated
and Machine
Learn in this
Process
Types of Unsupervised Learning

Visualization and
Anomaly detection and Association rule
Clustering dimensionality
novelty detection learning
reduction

—K-Means —One-class SVM —Principal Component —


Analysis (PCA) Apriori
—DBSCAN —Isolation
Forest —Eclat
—Hierarchical
Cluster Analysis
(HCA)
Reinforcement Learning is a very different beast. The learning system, called an agent in
this context, can observe the environment, select and perform actions, and get rewards in
return (or penalties in the form of negative rewards, must then learn by itself what is the
best strategy, called a policy, to get the most reward over time. A policy defines what action
the agent should choose when it is in a given situation.
Case 1- If agent reach to single
Reward 1 Reward -1 butterfly then reward 1
Case 2- If agent reach to four
butterfly then reward 4
Case 3- If agent reach to snake
then reward -1

Agent Reward 4
Note:- Frog is Agent here

You might also like