Machine Learning & Deep Learning - Theory & Python

Name: Machine Learning & Deep Learning - Theory & Python
Rating: 4.7 (4 reviews)

Master the Logic, Write the Code.

Created byHaris Jafri

Last updated 8/2026

English

English [Auto],

What you'll learn

Understand the core logic behind key Machine Learning algorithms using Infographics.
Grasp concepts like Regression, Classification, and Gradient Descent without Coding Pressure.
Build a Strong Conceptual Foundation for Deep Learning and Advanced ML Techniques.
Think like an ML engineer by focusing on Problem-Solving Logic, not Code Memorization.

Course content

19 sections • 121 lectures • 17h 20m total length

Theory Section Introduction0:11
K-NN Algorithm15:28
A Revision of the Famous Euclidean Distance Formula and its impact on Learning from Training Data Set to predict Labels from Features.

Data Science: Introduction6:16
An Introduction to Data, Science and Data Science!
Road to Wisdom2:48
Wisdom is a Valuable Entity provided you can extract it from Data.
Data Science to Machine Learning4:16
Data Science is the Systematic Study of Data. Machine Learning is the Special Case where Sole Focus is to predict and take decision after Studying and Learning from Data.
Machine Learning - The Very Basic12:45
How is Machine Learning different from Traditional Programming?
Supervised Machine Learning3:48
Classify or Regress. No Other Option!
Issues with Data13:20
We need to handle Data Set even before we begin Machine Learning.
Train Test Split2:40
Split the Data Set into Train and Test Data so that later you can use the Test Data for Model Evaluation.
Loss Function20:07
Punishment on Wrong Prediction !
Features and Target6:40
Features in a Data Set do not fall off from Sky !
Evaluation Metrics16:07
Once you come up with a Model. How to Evaluate its effectiveness?

Correct Classification Criteria6:02
How Machine know whether they have classified a record correctly or incorrectly !
Linearly Separable Data3:25
What are the Conditions a Data Set must comply to in order to call it Linearly Separable.
Data Record to Hyperplane4:00
What is the distance between a Record in n Dimensional Space with the Hyperplane existing in that n Dimensional Space.
The First Learning Algorithm3:57
The Primary Requirement of a Learning Algorithm is that it must Learn.
The Practical11:04
Let's implement Perceptron to a Data Set to see how it behaves. Aim is to find a Hypothesis.
Through the Origin11:27
Add an Additional Feature and see the Magic!

Limited Hypothesis2:42
It appears that Linear Classifier is a Limited Hypothesis. The Question is that "Is it?".
1D Polynomial Basis10:51
The Technique of Polynomial Basis Transformation Function on a Data Set with 1 Feature only.
nD Polynomial Basis11:08
The Technique of Polynomial Basis Transformation Function on a Data Set with Multiple Feature only.
Feature Encoding4:13
Label or One-Hot!
Feature Normalization3:35
Some work is required even with Numerical Features.
Vectorization3:33

A Simple Regression Tool6:00
The Basic Understanding of Regression.
Correlation Coefficient Method16:06
A Basic Method to come up with a Hypothesis for Regression.
Score of a Model5:28
We have discussed several Evaluation Criterion for Hypothesis used for Regression Problem Class. Let's discuss one more of it.
Convex Functions7:50
Understanding a Convex Function is essential to grasp ML Optimization Technique.
OLS - Direct Differentiation Solution8:54
Differentiate Directly. The Core behind OLS !
OLS - Matrix Solution15:29
A Faster Way to solve OLS Problem. The Core remains the same.
Linear Regression via Optimization21:52
An Optimal Way to approach the Linear Regression Problems.
Linear Regression with Feature Engineering5:33
Effects of Feature Engineering in Linear Regression

Buildup to LLC7:16
Why the need of an Additional Type of Classifier.
Euler Number5:23
The Base of Euler Number and where does it originate from.
Sigmoid Function17:26
Sigmoid Function is a Function that turns the Output of Simple Hypothesis into a Probabilistic One.
Threshold5:26
What to do with the Probabilistic Output? We need Labels, not a Probability.
Logistic Loss12:54
Understand the Loss that is related to Logistic Regression.
Linear Logistic Classifier13:59
The Application of LLC (Linear Regression) on a Small Data Set to understand how it Operates !

Requirements

No Pre-Requisites

Description

Are you overwhelmed by machine learning code but still unclear about how it actually works? You're not alone—and this course is here to change that.

"Machine Learning & Deep Learning - Theory & Python" is a unique, beginner-friendly course designed to help you truly understand the logic behind ML, and then practically implement it step-by-step.

Master the 'Why': Before diving into complex libraries, we use infographics, visual analogies, and clear logic to explain core concepts—like regression, classification, cost functions, and gradient descent—in a way that actually sticks.
Learn the 'How': With the newly integrated Python from Scratch modules, you will build the exact programming foundation needed to bring these theoretical concepts to life.

Once the logic is clear, transitioning to the code becomes natural and meaningful. This course is perfect for absolute beginners, non-programmers transitioning into tech, or developers who want to strengthen their conceptual understanding alongside their practical coding skills.

Don’t just memorize syntax—understand machine learning and deep learning from the inside out. You’ll stop treating ML models like a magic spell and start building them as logical structures with complete confidence.

Start your Machine Learning and Deep Learning journey with clarity, confidence, and real understanding.

Python shall also be discussed from the very beginning !

Who this course is for:

Absolute Beginners to Machine Learning
Aspiring Data Scientists with Weak Math Backgrounds
Programmers Looking to Understand ML Algorithms More Deeply
Students in Other Disciplines Exploring ML
Individuals Wanting a Refresher on Key Mathematical Concepts

Machine Learning & Deep Learning - Theory & Python

What you'll learn

Explore related topics

Course content

Glimpse2 lectures • 16min

The Very Basic10 lectures • 1hr 29min

Linear Classifiers4 lectures • 42min

The Perceptron6 lectures • 40min

Feature Representation6 lectures • 36min

Gradient Descent3 lectures • 26min

Linear Regression8 lectures • 1hr 27min

Machine Learning Essentials4 lectures • 29min

SVM - Hard Margin4 lectures • 25min

Logistic Regression6 lectures • 1hr 2min

Requirements

Description

Who this course is for: