Introduction to Machine Learning

Name: Introduction to Machine Learning
Rating: 4.4 (114 reviews)

Machine Learning, Supervised Learning, Unsupervised Learning, Regression, Classification, Clustering, Markov Models, HMM

Created byDr.Padmapriya G

Last updated 11/2025

English

English [Auto],

What you'll learn

Explore the fundamental mathematical concepts of machine learning algorithms
Apply linear machine learning model to perform regression and classification
Utilize mixture models to group similar data items
Develop macine learning models for time-series data prediction
Design ensemble learning model using various machine learning algorithms

Course content

5 sections • 18 lectures • 3h 25m total length

Machine Learning What and Why?12:19
Explore the definitions and differences of artificial intelligence, machine learning, and deep learning, and see how data-driven learning enables predictions and intelligent decisions.
Supervised and Unsupervised Learning14:17
Explore supervised learning with labeled data and a mapping function y = f(x), and compare unsupervised learning (clustering, dimensionality reduction, association rules) and reinforcement learning (agent, rewards) for decision making.
Polynomial Curve Fitting10:18
Explore polynomial curve fitting to model input x with training targets from sine pi x using y(x) and minimize the residual sum of squares to select the optimal degree m.
Probability Theory - Introduction and Fundamental Rules14:29
Learn the foundations of probability theory, including the sample space, events, union and conditional probability, and the product rules for independent and dependent events.
Probability - Bayes Rule and Independence and Conditional Independence10:57
Master Bayes rule and independence through conditional probability, the multiplication rule, and the total probability theorem, with practical examples and posterior calculations.
Probability - Random Variables and Density Function7:59
Explore random variables, including discrete and continuous types, and learn how probability density function, pmf, pdf, and cdf describe outcomes with examples and key properties.
Probability - Quantiles, Mean, Variance, Expectation and Covariance13:19
Explore quantiles, median, mean, variance, standard deviation, expectation, and covariance through practical examples to understand central tendency and dispersion in probability.
Introduction to Machine Learning

Robust Linear Regression12:00
Explore robust linear regression to mitigate outliers using the huber loss, compare MSE and MAE, and discuss laplace-based approaches for more reliable model fitting.
Ridge Linear Regression11:19
Learn ridge regression, an L2-regularized linear model that mitigates multicollinearity and overfitting by shrinking coefficients, balancing bias and variance with an optimal lambda.
Linear Discriminant Functions7:21
Master linear discriminant functions to separate classes by a linear combination of features, maximizing the ratio of between-class variance to within-class variance, and applying two-class and multi-class decision boundaries.
Linear Models for Regression

K- Means Clustering13:21
Explore k-means clustering, an unsupervised algorithm that partitions data into k clusters using centroid updates and distance minimization, with binary indicators and convergence, illustrated by an elbow method example.
PCA Solved Problem19:44
Explore principal component analysis through a hands-on 2D to 1D dimensionality reduction example, computing the mean, covariance matrix, eigenvalues and eigenvectors, and projecting data onto the first principal component.
Hierarchical Clustering5:37
Explore hierarchical clustering, an unsupervised machine learning method that groups unlabeled data into clusters by merging closest points and forming dendrograms. Learn about agglomerative and divisive approaches and linkage criteria.

Sequential Data and Markov Model10:49
Explore sequential data and Markov models, including first and second order chains, stationary and non stationary distributions, and how hidden Markov models capture dependencies with latent variables.
HMM Forward Algorithm19:21
Explore how the hmm forward algorithm computes the likelihood of observation sequences in a two-state hidden Markov model using initialization, recursion, termination, and dynamic programming.
HMM Backward Algorithm15:25
Learn the hidden Markov model backward algorithm, its dynamic programming recursion, and how it computes the probability of an observation sequence using transition and emission probabilities, with a solved example.

Bagging3:17
Explore bagging, a bootstrap aggregating ensemble method training multiple models on random samples with replacement. Combine predictions by aggregation to reduce overfitting and variance in classification and regression.
Stacking3:22
Learn stacking, an ensemble method that blends base model predictions with a meta model to boost accuracy and robustness, using Bayes models and other learners.

Requirements

No programming experience is need

Description

Course Description:
Unlock the power of machine learning with this comprehensive course designed for beginners and intermediate learners. You will be guided through the essential concepts, algorithms, and techniques driving machine learning today, building a solid understanding of how machines learn from data and solve real-world problems. This course is designed to help you grasp the theoretical underpinnings of machine learning while applying your knowledge through solved problems, making complex concepts more accessible.

What You'll Learn:

Core Principles of Machine Learning: Gain a deep understanding of how systems learn from data to make intelligent decisions.
Supervised Learning: Explore predictive modeling using algorithms like Linear Regression, and Support Vector Machines (SVM).
Unsupervised Learning: Master clustering techniques like k-Means and Hierarchical Clustering to discover patterns in data.
Regression and Classification: Learn how to model continuous outcomes (regression) and classify data into distinct categories (classification).
Clustering: Group similar data points to uncover hidden structures within large datasets.
Markov Models & Hidden Markov Models (HMMs): Understand probabilistic models that predict future states and learn how they are used to model sequences and temporal data. Through solved problems, you'll explore how these models work in practice, gaining insights into the theoretical foundation and practical application of HMMs in time-series data and sequential decision-making processes.

Machine learning is transforming industries by enabling systems to learn and make intelligent decisions from data. This course will equip you with a strong foundation in machine learning, focusing on problem-solving and theoretical understanding without the need for hands-on implementation.

Practical Application Through Solved Problems:

This course includes solved problems to illustrate how each algorithm and technique works in practice. These examples will help you apply theoretical concepts to real-world situations, deepening your understanding and preparing you to solve similar problems in your professional or academic career.

Through detailed explanations of algorithms, real-world examples, and step-by-step breakdowns of machine learning processes, you'll develop a solid grasp of the models and techniques used across various industries. This course is perfect for learners who want to master the core concepts of machine learning and engage with practical applications without diving into programming or technical implementation.

Course Highlights:

No Programming Required: Focus on understanding the theory behind machine learning algorithms and models.
Solve Real-World Problems: Work through practical examples to understand how to apply machine learning techniques to everyday challenges.
Evaluate Model Performance: Learn to assess, interpret, and refine machine learning models effectively.
Build a Strong Conceptual Foundation: Prepare for future practical applications in machine learning or data-driven fields.

Who Should Take This Course:

Students and Professionals: Ideal for those seeking an in-depth introduction to machine learning theory.
Enthusiasts with Basic Knowledge of Math and Programming: Perfect for those interested in machine learning concepts through solved problems and real-world examples.

Who this course is for:

Beginners for Machine learning

Introduction to Machine Learning

What you'll learn

Explore related topics

Course content

Introduction7 lectures • 1hr 24min

Linear Models for Regression3 lectures • 31min

Mixture Models and EM3 lectures • 39min

Hidden Markov Models3 lectures • 46min

Combining Models2 lectures • 7min

Requirements

Description

Who this course is for: