Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd
Upload
5 views

Lesson 2 - Machine Learning

The document provides an overview of supervised learning, a machine learning technique that trains algorithms on labeled datasets to predict outputs for new data. It discusses the advantages, such as high predictive accuracy and diverse applications, as well as disadvantages like data dependency and risk of overfitting. Additionally, it outlines the process of supervised learning, including data collection, preprocessing, model selection, and types of classification algorithms.

Uploaded by

purplee.hazee12
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
5 views

Lesson 2 - Machine Learning

The document provides an overview of supervised learning, a machine learning technique that trains algorithms on labeled datasets to predict outputs for new data. It discusses the advantages, such as high predictive accuracy and diverse applications, as well as disadvantages like data dependency and risk of overfitting. Additionally, it outlines the process of supervised learning, including data collection, preprocessing, model selection, and types of classification algorithms.

Uploaded by

purplee.hazee12
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 14

MACHINE LEARNING

Prepared by: Jonnifer C. Mandigma


2

z
OBJECTIVES
Supervised Learning
- Definition of Supervised Learning
- Advantage and Disadvantage of Supervised
Learning
- Process of Supervised Learning
- Types of Supervised Learning

2
WHAT IS
z

SUPERVISED
LEARNING?
4

SUPERVISED LEARNING
Supervised learning is a branch of machine learning
that involves training an algorithm on a labeled
dataset, where each training example consists of an
input-output pair. The "supervision" in supervised
learning refers to the presence of the correct outputs
(labels) that guide the learning process. The
primary objective is for the model to learn the
mapping from inputs to outputs so that it can predict
the labels for new, unseen data.
5

ADVANTAGE
Predictive Accuracy: Supervised learning can achieve high levels of
accuracy, especially when trained with a large amount of labeled data.
Models can generalize well to unseen data if properly tuned.
Clear Performance Metrics: The performance of supervised learning
models can be evaluated using various metrics (e.g., accuracy, precision,
recall, F1-score), making it easier to assess and compare different models.
Diverse Applications: Supervised learning techniques can be applied
across various domains, including finance (credit scoring), healthcare
(diagnosis prediction), and marketing (customer segmentation).
Algorithm Variety: There are numerous algorithms available, allowing
practitioners to choose the most suitable one for their specific problem,
whether it’s a linear model, tree-based model, or deep learning approach.
6

z
DISADVANTAGE
Data Dependency: Supervised learning requires a large and
representative labeled dataset. Obtaining this data can be resource-
intensive and time-consuming.
Risk of Overfitting: If a model becomes too complex, it may perform
exceptionally well on training data but poorly on unseen data. This
phenomenon, known as overfitting, requires techniques like
regularization or cross-validation to mitigate.
Limited to Available Data: The model's performance is inherently tied
to the quality and diversity of the training data. If the training data is
biased or unrepresentative, the model may produce biased or
inaccurate predictions.
Computationally Intensive: Some algorithms, especially those
involving deep learning, can be computationally intensive, requiring
significant hardware resources and longer training times.
PROCESS
z
OF SUPERVISED
LEARNING

Data Collection: Gather a dataset that includes both features (inputs) and
labels (outputs). This dataset can come from various sources, such as
databases, web scraping, or APIs.
Data Preprocessing: Clean and prepare the data for analysis. This includes:
•Handling missing values (imputation or removal).
•Normalizing or scaling features (especially important for algorithms sensitive
to feature magnitude).
•Encoding categorical variables (using techniques like one-hot encoding).
•Splitting the data into training and test sets to evaluate model performance.
Model Selection: Choose an appropriate supervised learning algorithm
based on the nature of the problem (classification or regression). This choice
can be guided by factors such as the size of the dataset, the dimensionality of
the data, and the specific application requirements.
TYPES OF SUPERVISED
z
LEARNING

Classification is a process of finding a function which helps in dividing


the dataset into classes based on different parameters. In Classification, a
computer program is trained on the training dataset and based on that
training, it categorizes the data into different classes. The task of the
classification algorithm is to find the mapping function to map
the input(x) to the discrete output(y).
Example: The best example to understand the Classification
problem is Email Spam Detection. The model is trained on the
basis of millions of emails on different parameters, and
whenever it receives a new email, it identifies whether the email
is spam or not. If the email is spam, then it is moved to the
Spam folder.
z
TYPES OF ML CLASSIFICATION
ALGORITHMS
Classification Algorithms can be further divided into the
following types:
• Logistic Regression
• K-Nearest Neighbours
• Support Vector Machines
• Kernel SVM
• Naive Bayes
• Decision Tree Classification
• Random Forest Classification
TYPES
z
OF ML CLASSIFICATION
ALGORITHMS

• Common Algorithms: Decision Trees: A flowchart-like structure used


for decision-making, where each node represents a feature, and
branches represent decision outcomes.
• Support Vector Machines (SVM): A method that finds the optimal
hyperplane that separates classes in high-dimensional space.
• Neural Networks: Composed of layers of interconnected nodes that
learn to recognize patterns through training.
• K-Nearest Neighbors (KNN): A non-parametric method that classifies
data points based on the majority class of their nearest neighbors.
z

EXAMPLE CODE
z

EXAMPLE CODE

OUTPUT
TYPES
z OF SUPERVISED LEARNING

Classification is a process of finding a function which helps in dividing


the dataset into classes based on different parameters. In Classification, a
computer program is trained on the training dataset and based on that
training, it categorizes the data into different classes. The task of the
classification algorithm is to find the mapping function to map
the input(x) to the discrete output(y).
Example: The best example to understand the Classification
problem is Email Spam Detection. The model is trained on the
basis of millions of emails on different parameters, and
whenever it receives a new email, it identifies whether the email
is spam or not. If the email is spam, then it is moved to the
Spam folder.
z

EXAMPLE CODE

OUTPUT

You might also like