IMT-344 Computer Vision introduced Mechatronics Engineering students to artificial vision methods for inspection, monitoring, and control applications. The course covered digital image processing, segmentation, visual feature extraction, image compression, video analysis, optical flow, and real-time computer vision workflows. It also introduced machine learning and deep learning approaches for visual recognition, including classical classifiers, convolutional neural networks, transfer learning, object detection, semantic and instance segmentation, attention mechanisms, transformers, and generative models. Students completed a collaborative final project using Python-based computer vision and machine learning tools.

This course introduced students to the practical foundations of deploying, managing, and monitoring machine learning systems in production. The module covered the full ML lifecycle, from developing models with Scikit-learn and TensorFlow to tracking experiments, versioning code and data, packaging models with Docker, testing ML pipelines, and monitoring model performance after deployment. Through practical sessions and case studies, students learned how to build more reproducible, scalable, and maintainable ML workflows using modern MLOps tools and practices.

This course introduced students to the main concepts, algorithms, and applications of unsupervised machine learning. The module covered clustering methods such as K-means, hierarchical clustering, DBSCAN, HDBSCAN, and Gaussian Mixture Models, as well as dimensionality reduction techniques including PCA, Factor Analysis, Independent Component Analysis, t-SNE, and UMAP. Students also explored more advanced topics such as autoencoders, graphical models, semi-supervised learning, clustering for word embeddings, and clustering for visual data. Through practical laboratories, paper discussions, and applied case studies, the course helped students understand how to discover hidden patterns, reduce complex feature spaces, and apply unsupervised learning techniques to real-world data problems.

This course introduced students to the main concepts, algorithms, and applications of unsupervised machine learning. The module covered clustering methods such as K-means, hierarchical clustering, DBSCAN, HDBSCAN, and Gaussian Mixture Models, as well as dimensionality reduction techniques including PCA, Factor Analysis, Independent Component Analysis, t-SNE, and UMAP. Students also explored more advanced topics such as autoencoders, graphical models, semi-supervised learning, clustering for word embeddings, and clustering for visual data. Through practical laboratories, paper discussions, and applied case studies, the course helped students understand how to discover hidden patterns, reduce complex feature spaces, and apply unsupervised learning techniques to real-world data problems.

This course introduced students to the foundations of data mining, from data collection and preprocessing to feature engineering, exploratory data analysis, visualisation, predictive modelling, clustering, and anomaly detection. The module covered the knowledge discovery process, structured and unstructured data processing, dimensionality reduction, regression, classification, segmentation, distance-based methods, and model evaluation. Through practical laboratories, guided exercises, and a final applied project, students developed Python-based data mining solutions for discovering patterns, extracting insights, and supporting decision-making in business or institutional contexts.

This course introduced students to essential software engineering practices for building reliable and maintainable data science projects. The module covered Python programming, data structures, object-oriented programming, Python environments and IDEs, file and directory management, modules and packages, coding best practices with PEP8, version control systems, and containerised deployment with Docker. Through practical sessions and a final project, students learned how to organise code, manage dependencies, apply software development principles, and prepare data science applications for reproducible development and deployment.

This course introduced students to the foundations of intelligent systems and artificial intelligence, covering both symbolic and data-driven approaches. The module explored core AI concepts, rational agents, state-space modelling, uninformed and informed search algorithms, machine learning, and neural networks. Students applied NumPy, Scikit-learn, and TensorFlow to solve problems involving regression, classification, clustering, association, artificial neural networks, and deep learning. Through theoretical units, practical implementation tasks, and a final course project, students developed intelligent systems capable of reasoning, learning from data, and solving real-world computational problems.

This technical course introduced participants to the foundations of machine learning, natural language processing, and chatbot development. The course covered supervised and unsupervised learning, text processing with Python and NLTK, introductory NLP and deep learning concepts, and the development of conversational assistants using the Rasa framework. Participants also explored deployment and monitoring considerations for NLP models, with practical sessions leading to the presentation of chatbot projects.

This course introduced participants to the foundations and practical applications of computer vision, with a focus on developing solutions aligned with the Sustainable Development Goals. The programme covered image formation, image processing, point operations, filtering, edge detection, image transforms, morphological operations, segmentation, motion analysis, data processing, machine learning, neural networks, convolutional neural networks, transfer learning, object detection, semantic segmentation, instance segmentation, and model deployment. Through lectures, laboratory notebooks, office hours, and final projects, participants learned how to build computer vision applications using Python-based tools and apply them to real-world social and environmental challenges. The course was delivered as a three-month remote bootcamp, with 60 accepted participants and 40 finalists from six cities in Bolivia.

This course introduced students to the foundations and practical applications of computer vision for industrial environments. The module covered the main stages of a computer vision system, including image acquisition, preprocessing, segmentation, representation, feature extraction, recognition, interpretation, and compression. Students explored topics such as colour spaces, camera and lighting selection, image processing, spectral filters, morphological techniques, automated visual inspection, object recognition, and introductory machine learning methods for image analysis. Through lectures, practical laboratories, paper discussions, and a final mini-project, students learned how to design and implement computer vision pipelines for tasks such as defect detection, surveillance, robotics, and automated industrial inspection.

This course introduced students to the core principles of artificial intelligence and their practical application in technology-driven decision-making. The module covered intelligent agents, search agents, AI development environments, Python data structures, object-oriented programming, automated data processing, machine learning, deep learning, and algorithmic bias and fairness. Through lectures, group laboratories, an individual exam, and a final project, students learned how to design and implement basic AI solutions using Python-based tools while considering both technical and methodological aspects of intelligent systems.

This course introduced students to the foundations of data science, data mining, and descriptive modelling for discovering patterns in structured and unstructured datasets. The module covered Python programming, object-oriented programming, relational databases with SQL, Python–SQL integration, feature engineering, dimensionality reduction, PCA, clustering methods such as K-means, DBSCAN, HDBSCAN, hierarchical clustering, Gaussian Mixture Models, association rules, anomaly detection, and large-scale unstructured data processing. Through laboratories, in-class exercises, case study presentations, and a final project, students learned how to process, analyse, and model data to support predictive and descriptive decision-making tasks.

This course introduced students to practical data modelling techniques for structured and unstructured data. The module covered Python data structures, feature engineering, dimensionality reduction, PCA, supervised learning for regression and classification, evaluation metrics, hyperparameter optimisation, cross-validation, boosting models, unsupervised learning, clustering metrics, anomaly detection, association rules, introductory NLP, deep learning, TensorFlow/Keras, convolutional neural networks, and transfer learning. Through laboratories, in-class exercises, exams, and a final course project, students developed applied machine learning workflows for analysing, modelling, and extracting insights from diverse data sources.

This course introduced students to the core concepts, technologies, and architectures behind Internet of Things systems. The module covered the evolution of computing, IoT devices and sensors, cyber-physical data collection, sensing and actuation, communication mechanisms, IoT architectures, service-oriented solutions, and practical implementation examples. Students also explored the use of Arduino with C and Raspberry Pi with Python, as well as key considerations for designing connected systems in real-world environments. Through theoretical sessions, guided laboratories, readings, and a final project, students developed a practical understanding of how IoT solutions connect physical objects, data, and digital services across domains such as smart cities, healthcare, logistics, transportation, and security.

This course introduced students to the foundations of computer programming and algorithmic problem-solving. The module covered computer systems, problem analysis, pseudocode, flowcharts, algorithm design, sequential structures, conditional statements, loops, nested loops, standard operators and functions, and string manipulation. Students progressed from representing solutions as algorithms to implementing programs in a high-level programming language, developing the logical and practical skills needed to solve computational problems through structured programming.