AI Machine Learning Models
Professor
Valdis Saulespurens
About the professor
Valdis Saulespurēns has been implementing various AI solutions for more than 20 years. In addition to teaching programming courses at RTU and RBS, Valdis uses machine learning for big data aggregation, processing, and analysis at the National Library of Latvia.
Course Description
This intensive course provides a comprehensive foundation in machine learning, equipping participants with the skills to build and deploy effective models. By delving into core concepts, algorithms, and practical applications, learners will gain hands-on experience in data preprocessing, model training, and evaluation. This course empowers individuals to apply machine learning techniques to solve real-world problems across various industries and drive innovation. Upon completion, participants will be equipped to confidently tackle complex data challenges and contribute to data-driven decision-making within their organizations.
Course Goals
Provide an understanding of machine learning fundamentals and key models.
Develop skills in data processing and preparation for creating ML models.
Train participants to select and apply appropriate ML algorithms for specific problems.
Learn how to evaluate and improve the performance of ML models using validation and testing techniques.
After the course participants will be able to:
Identify different machine learning methods
Evaluate the relevance of the methods to the problems they are interested in
Use the opportunities offered by AI to foster innovation
Make data-driven decisions
Course will be:
Online and In Person
Prerequisites
- Basic knowledge of programming (Python preferred).
- Basic knowledge of statistics and data analysis.
- Basic knowledge in linear algebra and mathematics.
- Previous experience in data science or machine learning is preferred but not required.
Teaching methods used:
- Theoretical lectures with practical examples.
- Hands-on tasks and exercises using Python and popular ML libraries (e.g. scikit-learn, TensorFlow, PyTorch).
- Group discussions and project work.
- Case studies and real-world problem solving.
- Lecturer’s advice and feedback on participants’ work.
Topic 1
Introduction to the basics of machine learning
What is machine learning? Overview and Applications.
Types of Machine Learning: Supervised, Unsupervised and Reinforcement Learning.
Key ML concepts and terminology.
Overview of ML processes: Data preparation, model training, validation and application.
Topic 2
Data processing and preparation
Data cleaning and pre-processing.
Data transformations and feature engineering.
Splitting the data into training and testing sets.
Practical lesson: Data preparation for ML model in Python environment.
Topic 3
Linear models and regression analysis
Linear regression and multivariate regression.
Regularity: Ridge and Lasso Regression.
Classification tasks with the help of linear models (Logistic regression).
Practical Lesson: Training and Validation of Linear and Logistic Regression Models.
Topic 4
Classification algorithms
K-Nearest Neighbors (KNN) algorithm.
Support vector machines (SVM).
Decision trees and ensemble methods (Random Forest, XGBoost).
Hands-on Lesson: Building Classification Models and Evaluating Performance.
Topic 5
Neural networks and deep learning
Artificial neural networks: Structure and principle of operation.
Fundamentals of Deep Learning and Neural Network Training.
Overview of Keras and TensorFlow.
Hands-on: Building and Training a Simple Neural Network.
Topic 6
Unsupervised learning methods
Clustering: K-means and hierarchical clustering.
Principal component analysis (PCA) and dimensionality reduction.
Anomaly detection.
Practical lesson: Application of clustering and PCA to real data.
Topic 7
Model validation and hyperparameter optimization
K-fold cross-validation method and its application.
Hyperparameter optimization with GridSearchCV and RandomizedSearchCV.
Comparing and choosing models.
Practical lesson: Validation and optimization of models.
Topic 8
Project development and final discussion
Project task formulation and data selection.
ML model building, training and testing.
Project presentation and discussion.
Final course discussion and feedback.
Professor
Valdis Saulespurens
About the professor
Valdis Saulespurēns has been implementing various AI solutions for more than 20 years. In addition to teaching programming courses at RTU and RBS, Valdis uses machine learning for big data aggregation, processing, and analysis at the National Library of Latvia.
Course Description
This intensive course provides a comprehensive foundation in machine learning, equipping participants with the skills to build and deploy effective models. By delving into core concepts, algorithms, and practical applications, learners will gain hands-on experience in data preprocessing, model training, and evaluation. This course empowers individuals to apply machine learning techniques to solve real-world problems across various industries and drive innovation. Upon completion, participants will be equipped to confidently tackle complex data challenges and contribute to data-driven decision-making within their organizations.
Course Goals
Provide an understanding of machine learning fundamentals and key models.
Develop skills in data processing and preparation for creating ML models.
Train participants to select and apply appropriate ML algorithms for specific problems.
Learn how to evaluate and improve the performance of ML models using validation and testing techniques.
After the course participants will be able to:
Identify different machine learning methods
Evaluate the relevance of the methods to the problems they are interested in
Use the opportunities offered by AI to foster innovation
Make data-driven decisions
Course will be:
Online and In Person
Prerequisites
- Basic knowledge of programming (Python preferred).
- Basic knowledge of statistics and data analysis.
- Basic knowledge in linear algebra and mathematics.
- Previous experience in data science or machine learning is preferred but not required.
Teaching methods used:
- Theoretical lectures with practical examples.
- Hands-on tasks and exercises using Python and popular ML libraries (e.g. scikit-learn, TensorFlow, PyTorch).
- Group discussions and project work.
- Case studies and real-world problem solving.
- Lecturer’s advice and feedback on participants’ work.
Topic 1
Introduction to the basics of machine learning
What is machine learning? Overview and Applications.
Types of Machine Learning: Supervised, Unsupervised and Reinforcement Learning.
Key ML concepts and terminology.
Overview of ML processes: Data preparation, model training, validation and application.
Topic 2
Data processing and preparation
Data cleaning and pre-processing.
Data transformations and feature engineering.
Splitting the data into training and testing sets.
Practical lesson: Data preparation for ML model in Python environment.
Topic 3
Linear models and regression analysis
Linear regression and multivariate regression.
Regularity: Ridge and Lasso Regression.
Classification tasks with the help of linear models (Logistic regression).
Practical Lesson: Training and Validation of Linear and Logistic Regression Models.
Topic 4
Classification algorithms
K-Nearest Neighbors (KNN) algorithm.
Support vector machines (SVM).
Decision trees and ensemble methods (Random Forest, XGBoost).
Hands-on Lesson: Building Classification Models and Evaluating Performance.
Topic 5
Neural networks and deep learning
Artificial neural networks: Structure and principle of operation.
Fundamentals of Deep Learning and Neural Network Training.
Overview of Keras and TensorFlow.
Hands-on: Building and Training a Simple Neural Network.
Topic 6
Unsupervised learning methods
Clustering: K-means and hierarchical clustering.
Principal component analysis (PCA) and dimensionality reduction.
Anomaly detection.
Practical lesson: Application of clustering and PCA to real data.
Topic 7
Model validation and hyperparameter optimization
K-fold cross-validation method and its application.
Hyperparameter optimization with GridSearchCV and RandomizedSearchCV.
Comparing and choosing models.
Practical lesson: Validation and optimization of models.
Topic 8
Project development and final discussion
Project task formulation and data selection.
ML model building, training and testing.
Project presentation and discussion.
Final course discussion and feedback.