Introduction to Data Science

By

​

S.V.V.D.Jagadeesh

Sr. Assistant Professor

Dept of Artificial Intelligence & Data Science

​

​

LAKIREDDY BALI REDDY COLLEGE OF ENGINEERING

• Session Outcomes
• Machine Learning Modeling Process
• Feature Engineering and Model Selection
• Training the Model
• Validating a Model
• Predicting New Observations

​

​

​

​

S.V.V.D.Jagadeesh

Saturday, January 4, 2025

Previously Discussed Topics

LBRCE

IDS

At the end of this session, Student will be able to:

• Understand the different types of learning(Understand- L2)

S.V.V.D.Jagadeesh

Saturday, January 4, 2025

Session Outcomes

LBRCE

IDS

■ Supervised learning techniques attempt to discern results and learn by trying to find patterns in a labeled data set.

Human interaction is required to label the data.

■ Unsupervised learning techniques don’t rely on labeled data and attempt to find patterns in a data set without human interaction.

■ Semi-supervised learning techniques need labeled data, and therefore human interaction, to find patterns in the data set, but they can still progress toward a result and learn even if passed unlabeled data as well

S.V.V.D.Jagadeesh

Saturday, January 4, 2025

Types of Machine Learning

LBRCE

IDS

• As stated before, supervised learning is a learning technique that can only be applied on labeled data.

S.V.V.D.Jagadeesh

Saturday, January 4, 2025

Supervised Learning

LBRCE

IDS

• It’s generally true that most large data sets don’t have labels on their data, so unless you sort through it all and give it labels, the supervised learning approach to data won’t work.
• Instead, we must take the approach that will work with this data because

■ We can study the distribution of the data and infer truths about the data in different parts of the distribution.

■ We can study the structure and values in the data and infer new, more meaningful data and structure from it.

S.V.V.D.Jagadeesh

Saturday, January 4, 2025

Unsupervised Learning

LBRCE

IDS

• Certain variables can be immediately available while others can only be inferred and are therefore missing from your data set.
• The first type of variables are known as observable variables and the second type are known as latent variables.
• It definitely influences their judgement of you but its value isn’t clear.
• Deriving or inferring latent variables and their values based on the actual contents of a data set is a valuable skill to have because

■ Latent variables can substitute for several existing variables already in the data set.

S.V.V.D.Jagadeesh

Saturday, January 4, 2025

Unsupervised Learning

LBRCE

IDS

■ By reducing the number of variables in the data set, the data set becomes more manageable, any further algorithms run on it work faster, and predictions may become more accurate.

■ Because latent variables are designed or targeted toward the defined research goal, you lose little key information by using them.

S.V.V.D.Jagadeesh

Saturday, January 4, 2025

Unsupervised Learning

LBRCE

IDS

• We can use our unsupervised machine learning techniques to analyze what we have and perhaps add labels to the data set, but it will be prohibitively costly to label it all.
• Our goal then is to train our predictor models with as little labeled data as possible.
• This is where semi-supervised learning techniques come in—hybrids of the two approaches we’ve already seen.
• A common semi-supervised learning technique is label propagation.
• In this technique, you start with a labeled data set and give the same label to similar data points. This is similar to running a clustering algorithm over the data set and labeling each cluster based on the labels they contain. I

S.V.V.D.Jagadeesh

Saturday, January 4, 2025

Semi-Supervised Learning

LBRCE

IDS

• In this technique, you start with a labeled data set and give the same label to similar data points.
• This is similar to running a clustering algorithm over the data set and labeling each cluster based on the labels they contain.
• One special approach to semi-supervised learning worth mentioning here is active learning.
• In active learning the program points out the observations it wants to see labeled for its next round of learning based on some criteria you have specified.

S.V.V.D.Jagadeesh

Saturday, January 4, 2025

Semi-Supervised Learning

LBRCE

IDS

• Session Outcomes
• Types of Machine Learning
• Supervised Learning
• Un-Supervised Learning
• Semi-Supervised Learning

​

​

​

​

​

S.V.V.D.Jagadeesh

Saturday, January 4, 2025

Summary

LBRCE

IDS