Mastering Machine Learning within Artificial Intelligence

Name: Mastering Machine Learning within Artificial Intelligence
Rating: 4.7 (56 reviews)

Learn to build powerful Machine Learning algorithms in Python using scikit-learn, TensorFlow, PyTorch, and more.

Created byMassimiliano Sorrentino

Last updated 2/2026

English

What you'll learn

Learn what machine learning is
Learn the basic principles of machine learning
Learn what artificial neurons are
Learn the difference between machine learning and traditional programming
Apply supervised learning techniques using Python libraries like scikit-learn
Implement unsupervised learning algorithms such as clustering
Build reinforcement learning agents and train them in simulated environments
Understand and evaluate machine learning models using real-world datasets
Visualize and interpret model results to gain actionable insights
Compare the strengths and weaknesses of SL, UL, and RL in different scenarios
Develop machine learning pipelines from data preprocessing to model deployment
Use Python to experiment with hyperparameter tuning and model optimization
Build an RNN in PyTorch to predict hourly temperature from real weather data and visualize real vs predicted values.
Use Cursor and AI prompting to turn ML specifications into runnable code, from data preprocessing to model training and evaluation.

Course content

7 sections • 35 lectures • 6h 55m total length

What is machine learning?3:20
Understand what “Machine Learning” means and where it is used in real-world applications
How Machine Learning Works in Practice3:03
Learn how machine learning systems differ from traditional programming and why this approach is so powerful
The Three Main Types of Machine Learning4:36
Discover the core paradigms of machine learning and when to use each one
Supervised Learning Fundamentals3:31
Learn how supervised learning works, from labeled data to model training and prediction
Linear Regression with Classic Programming11:37
See how to implement linear regression step by step using traditional programming techniques
Linear Regression with Machine Learning6:55
Learn how to train a linear regression model with a machine learning workflow and compare it to the classic approach
Full Batch, Mini Batch and Stochastic Gradient Descent5:56
Understand and compare the main variants of gradient descent to optimize your models efficiently
The Artificial Neuron and Neural Networks6:26
Explore how artificial neurons work and how they combine to form neural networks
Linear Regression with a Single Neuron2:50
Learn how a single neuron can learn a linear regression and see it in action on real data
Machine Learning Basics – Supervised, Unsupervised and Reinforcement Learning

Linear Regression with the Algebraic Method (Part 1)13:04
Linear Regression with the Algebraic Method (Part 2)8:40
One Dimensional Linear Regression (Algebraic Method)23:28
Learn how to compute a 1D linear regression with the algebraic method and visualize the results with plots
Linear Regression with Neural Networks29:43
Train a neural network to solve a linear regression problem and compare it with the analytic solution
Building a Simple Neural Network for Regression8:07
Build and train a small neural network to perform multivariate linear regression in practice
Linear Regression with Two Outputs (Part 1)13:49
This lesson explains how to implement linear regression with two outputs using Python, NumPy, Pandas and PyTorch, starting from a small dataset and building a simple neural network that learns to predict two target variables at the same time.
It covers how to prepare a multivariate dataset in Pandas, split inputs and targets, define a multi‑output PyTorch model, choose loss and optimizer, train it step by step, and evaluate predictions on example inputs.
Errata corrige
Around minute 7:44, line 23 of the code to select the last two columns of the DataFrame is incorrect; the correct code is df.iloc[:, -2:] to include the last two columns.
The downloadable script provided with the lesson already contains the correct version of this line, so students can safely refer to the attached material.
Linear Regression with Two Outputs (Part 2)15:27

A Deep Neural Network for Digit Classification23:00
Discover how a deep neural network can recognize handwritten digits from images
Defining the Classification Network in Code17:55
Learn how to implement the architecture of a classification network step by step in code
Training the Digit Recognition Model26:31
Train the digit recognition model and monitor its learning progress and accuracy
Testing and Evaluating the Model12:41
Test the model on new images, evaluate its performance in detail, and learn how to run random tests on any classification model
From Pixels to Predictions with Convolutional Neural Networks5:57
This lesson offers a clear, practical introduction to Convolutional Neural Networks, the backbone of modern computer vision. We’ll explore how CNNs process images through convolutional layers, filters, and pooling, understand their internal structure, and follow the dimensional changes step-by-step using the MNIST dataset as an example. With intuitive explanations, diagrams, and PyTorch code, you’ll see exactly how these networks learn to detect patterns — from simple edges to complex shapes — and transform raw pixels into accurate predictions.

Introduction to Recurrent Neural Networks10:57
In this lesson you’ll learn the core structure of recurrent neural networks (RNNs), how they process sequential data, and when they are the right choice for your machine learning projects.
Temperature Prediction with RNN in PyTorch – Built with Cursor and AI Prompting10:09
Learn how to build an hourly temperature prediction model with a simple RNN using Cursor and AI prompting. You’ll start from a written specification (prompt) that describes data, preprocessing, model, training, and evaluation; then use Cursor to generate a complete, runnable PyTorch script. The lesson shows how to fetch real historical weather from a meteo API, preprocess it with pandas and MinMaxScaler, implement a custom PyTorch Dataset for 24-step sequences with a 1-step-ahead target, define and train a simple RNN (input size 1, hidden size 32), and evaluate and visualize predictions. By the end you’ll understand how to go from a clear prompt to a working time series model with Cursor and AI-assisted coding.
Main points of the lesson:
Use Cursor and a detailed prompt to generate a full PyTorch RNN project from a specification
Fetch real hourly temperature data via the a meteo API
Preprocess time series with MinMaxScaler and build sliding-window sequences
Implement a custom PyTorch Dataset and DataLoader for RNN input
Define and train a simple RNN in PyTorch and visualize real vs predicted temperature

K Means Clustering: Theory and Intuition10:34
Learn how the K‑Means clustering algorithm works and when to use it on real datasets
Implementing K Means Clustering in Python13:29
Implement K‑Means from scratch in Python and apply it to sample data
DBSCAN Clustering: Theory and Intuition6:30
Understand how DBSCAN discovers clusters of arbitrary shape and handles noise points
Implementing DBSCAN Clustering in Python7:48
Learn to implement DBSCAN in Python using scikit‑learn and experiment with its main parameters
Dimensionality Reduction: Key Concepts5:16
Discover why dimensionality reduction is useful and the main techniques used in practice
Dimensionality Reduction in Python (PCA)12:13
Write and run a Python script that applies PCA to reduce dimensionality and visualize the results

Introduction to Reinforcement Learning6:12
Learn the basic concepts of agents, environments, rewards and policies in reinforcement learning
Solving CartPole with PPO (Stable Baselines3)21:43
Train a PPO agent to solve the classic CartPole environment step by step using stable‑baselines3
Lunar Lander with PPO: From Setup to Landing23:49
Configure, train and test a PPO agent to land a lunar module in the LunarLander environment with stable‑baselines3 and gymnasium
Building a Custom Reinforcement Learning Environment34:12
Design a custom environment and connect it to a reinforcement learning agent to solve your own optimization problem

Requirements

Some knowledge is linear algebra is preferred, but not absolutely necessary
You must know object oriented programming, preferably in Python

Description

This hands-on machine learning course builds a clear, practical foundation in the field, moving from core ideas to real implementations. We open with what machine learning is, how it works, and the main application areas, then introduce supervised learning through the most accessible gateway: linear regression. You’ll see the contrast between traditional programming and the machine-learning approach, and learn how gradient descent works in practice—comparing full-batch, mini-batch, and stochastic updates. From there we step into the artificial neuron and use it to implement linear regression with a single neuron, cementing intuition before scaling up. A short quiz consolidates the essentials on supervised, unsupervised, and reinforcement learning.

We then dive deeper into regression: the algebraic method to ground your math intuition, one-dimensional regression, and the ML training pipeline for linear models, culminating in a truly simple neural network and extensions to multiple dependent variables. Next, in classification, you’ll assemble a deep neural network, define the target classes, and practice training and testing a model—connecting theory to usable evaluation workflows.

When moving to sequential data, you’ll learn how to predict hourly temperature with an RNN in PyTorch. In a dedicated lesson built with Cursor and AI prompting, you start from a detailed specification and use Cursor to generate a complete, runnable script: you’ll fetch real historical weather from meteo API, preprocess time series with MinMaxScaler and sliding-window sequences, implement a custom PyTorch Dataset and DataLoader, and train a simple RNN to forecast the next hour from the last 24, then evaluate and visualize real vs predicted temperature. The lesson shows how to go from a clear prompt to a working time series model with Cursor and AI-assisted coding.

Shifting to unsupervised learning, you’ll first understand and then code both K-Means and DBSCAN, before applying dimensionality reduction techniques and putting them into practice to make high-dimensional data tractable and visualizable. Finally, you’ll explore reinforcement learning: from the core principles to classic control problems like CartPole and LunarLander, and even design a custom environment, learning to reason in terms of states, actions, rewards, and policies. The course wraps up with a concise conclusion to help you review key takeaways and plan your next steps. Throughout, the emphasis is on conceptual clarity, clean code, and repeatable workflows—so you don’t just learn ML, you learn to build with it.

Who this course is for:

People who want to approach machine learning.
People who want to pursue a career in machine learning
People who want to use Cursor and AI prompting to build machine learning projects from clear specifications.

Mastering Machine Learning within Artificial Intelligence

What you'll learn

Explore related topics

Course content

Foundations of Machine Learning9 lectures • 48min

Regression Models in Practice7 lectures • 1hr 52min

Classification with Neural Networks5 lectures • 1hr 26min

Sequence Modeling with Neural Networks2 lectures • 21min

Unsupervised Learning: Clustering and Dimensionality Reduction6 lectures • 56min

Reinforcement Learning in Action4 lectures • 1hr 26min

Course Wrap Up and Next Steps2 lectures • 6min

Requirements

Description

Who this course is for: