The course Supervised Learning in ML it's yours a gateway to the world of artificial intelligence and machine learning. In an era where Data is the new oil, the ability to derive value from them is in high demand. This course will provide you with a a sound understanding of the fundamentals of supervised learning, showing you how to distinguish between classification and regression, and to evaluate models using key metrics. You will learn how to prepare data effectively, dominating cleaning techniques and dimensionality reduction, ensuring that you can to turn raw data into valuable information. You’ll also explore from basic models such as the linear regression and the decision trees, up to advanced models such as SVM y assembly methods, developing key skills to tackle complex problems. With a online approach, this course offers you flexibility to learn at your own pace, getting ready for a a labour market that is constantly growing and evolving.
Supervised Learning in ML
AI Academy
3 pm
Introduction
Objectives
-
Understand the definition and application of supervised learning in real problems.
-
Distinguish between supervised, unsupervised and reinforcement learning.
-
Identifying and categorising problems in classification and regression.
-
Implement a supervised ML pipeline, from the from preparation to assessment.
-
Evaluate models by means of key metrics y cross-validation.
-
Perform data cleansing and management of missing values y outliers.
-
Apply techniques for scaling, normalisation and dimensionality reduction.
Table of Contents
TEACHING UNIT 1. FUNDAMENTALS OF SUPERVISED LEARNING
1. Definition of supervised learning
2. Differences from other paradigms: unsupervised and reinforcement-based
3. Types of problems: classification vs regression
4. A typical supervised machine learning pipeline
5. Model evaluation: Key metrics and cross-validation
TEACHING UNIT 2. DATA PREPARATION AND FEATURE ENGINEERING
1. Data quality: data cleaning, handling missing values and outliers
2. Coding categorical variables
3. Scaling and normalisation of features
4. Selection and extraction of relevant features
5. Dimension reduction techniques (PCA, LDA)
TEACHING UNIT 3. BASIC SUPERVISED LEARNING MODELS
1. Linear regression and its variants
2. Linear classifiers: perceptron and logistic regression
3. Decision trees: structure, pruning and partitioning criteria
4. Nearest neighbours (k-NN): simplicity and limitations
5. Specific evaluation metrics by model type
TEACHING UNIT 4. ADVANCED MODELS AND ASSEMBLY
1. Support Vector Machines (SVMs): margins and kernels
2. Bagging, Boosting and Stacking
3. Random Forest and its advantages over individual trees
4. Gradient Boosting Machines
5. Hyperparameter tuning and nested validation
More related courses
Your questions answered
Why choose Educa.Pro?
Educa.Pro enables organisations to centralise training management, personalise learning and gain clear insights into the impact of training programmes. Thanks to its AI-powered technology, organisations can optimise their learning strategies, enhance talent development and make data-driven decisions.
Can the courses be taken at your own pace?
Yes. Most of the courses on Educa.Pro are self-paced and on-demand, allowing users to progress at their own pace without missing out on progress tracking or assessments, which makes it easier to fit them around work or study commitments.
What levels of security and compliance does the platform offer?
Educa.Pro complies with security standards designed to protect user and organisational data. Furthermore, it supports the traceability of certifications, digital signatures and the management of assessments, thereby ensuring regulatory and legal compliance in both educational and corporate environments.
What support and guidance does Educa.Pro offer?
The Educa.Pro team offers comprehensive support throughout implementation, roll-out and adoption, ensuring that organisations get the most out of the platform and achieve measurable results from day one.