Training: Machine Learning & AI
Level
BeginnerDuration
32h / 4 daysDate
Individually arrangedPrice
Individually arrangedTraining: Machine Learning & AI
The “Machine Learning & AI” course is designed to provide participants with practical skills in artificial intelligence (AI – Artificial Intelligence). It prepares professionals and employees from various industries to apply AI technologies in their work and projects. With AI becoming increasingly widespread across industries, demand for specialists with machine learning skills is rapidly growing. Since the field of AI evolves dynamically, regular training and knowledge updates are essential for staying competitive.
What will you learn?
- Understand the role of data in machine learning and principles of data preparation
- Apply machine learning algorithms to solve practical problems
- Learn the main types of machine learning and core algorithms in each area
- Prepare and deliver a Proof of Concept (POC) project
Important prerequisites
- The training is based on Python and popular libraries such as pandas, NumPy, scikit-learn, PyTorch, and others.
- The training is delivered using Google Colaboratory.
- Participants only need a standard Google account (e.g., Gmail).
Who is this training for?
IT specialists and programmers who want to expand their skills with machine learning and AI programming-
Engineers (robotics, automation, electronics, etc.) interested in applying AI systems in their projects
-
Data analysts (both beginners and experienced) who want to explore data analysis techniques with AI and gain more advanced insights
Training Program
-
Day 1 – Data
-
Introduction: What is Machine Learning (ML)?
- Definition and key differences between traditional programming and ML
- History and evolution of ML, industry impact
- Types of learning: supervised, unsupervised, reinforcement
-
Data – EDA (Exploratory Data Analysis) & Preprocessing
- Why data matters in ML and where it comes from
- Exploratory data analysis: visualizations, descriptive statistics, outlier detection
- Data preparation: cleaning missing values, encoding categorical variables, scaling and normalization, train/test split
- Workshop: Data preprocessing and EDA with real datasets (Google Colab, Python)
-
Day 2 – Supervised Learning
- Characteristics of supervised learning: problems solved, pros & cons
-
Regression
- Linear, polynomial, and logistic regression
-
Classification
- Decision trees, SVM, k-nearest neighbors (k-NN)
- Evaluation metrics: MSE, precision, recall, F1, ROC curve, AUC
- Workshop: Implementing supervised algorithms and building a POC with real datasets (Google Colab, Python)
-
Day 3 – Unsupervised Learning
- Characteristics of unsupervised learning: problems solved, pros & cons
-
Clustering
- k-means, DBSCAN, hierarchical clustering
-
Dimensionality Reduction
- PCA, t-SNE
- Workshop: Applying unsupervised learning algorithms and building a POC with real datasets (Google Colab, Python)
-
Day 4 – Neural Networks
- Introduction: What are neural networks, applications, pros & cons
-
Basics
- Perceptrons, network architecture, activation functions, forward & backpropagation
-
Deep Learning
- Deep neural networks, CNNs for image analysis
- Workshop: Implementing neural networks and building a POC with real datasets (Google Colab, Python)
