• Welcome to your new Gnomio site

    Now, you are in control!

    Moodle is an open-source Learning Management System (LMS) that provides educators with the tools and features to create and manage online courses. It allows educators to organize course materials, create quizzes and assignments, host discussion forums, and track student progress. Moodle is highly flexible and can be customized to meet the specific needs of different institutions and learning environments.

    Moodle supports both synchronous and asynchronous learning environments, enabling educators to host live webinars, video conferences, and chat sessions, as well as providing a variety of tools that support self-paced learning, including videos, interactive quizzes, and discussion forums. The platform also integrates with other tools and systems, such as Google Apps and plagiarism detection software, to provide a seamless learning experience.

    Moodle is widely used in educational institutions, including universities, K-12 schools, and corporate training programs. It is well-suited to online and blended learning environments and distance education programs. Additionally, Moodle's accessibility features make it a popular choice for learners with disabilities, ensuring that courses are inclusive and accessible to all learners.

    The Moodle community is an active group of users, developers, and educators who contribute to the platform's development and improvement. The community provides support, resources, and documentation for users, as well as a forum for sharing ideas and best practices. Moodle releases regular updates and improvements, ensuring that the platform remains up-to-date with the latest technologies and best practices.

    Links of interest:

    (You can edit or remove this text)

Available courses

Natural Language Processing (NLP) and Text Mining

This course provides a theoretical and methodological introduction to the most widely used and effective current techniques, strategies, and toolkits for natural language processing (NLP) and text mining.

Upon completion of this course, doctoral students will be able to:

  1. Develop an understanding of the principles, formal methods, and strategies used in the design and analysis of language-processing algorithms.

  1. Describe in depth the major algorithms used in NLP, including lexical, morphological, syntactic, and semantic analysis.

  2. Develop an individual project, gaining practical understanding of NLP workflows along with tools and methods for evaluating results of NLP-based exploratory and analytical strategies.

  3. Access and apply popular linguistic databases, including WordNet and treebanks.

  4. Evaluate digital archives and textual sources, and identify the opportunities textual repositories offer for computational approaches to literature, history, law, medicine, business, and the social sciences.

  5. Extract information from unstructured text, including topic identification and named-entity recognition.

  6. Analyze linguistic structure in text, including parsing and semantic analysis.

  7. Integrate techniques drawn from diverse fields such as linguistics and artificial intelligence.

  8. Build a functional NLP application, integrating standard NLP modules, through hands-on training.

Foundations of Software Engineering

This course provides a comprehensive study of software engineering principles, processes, and tools required for the development of complex, large-scale systems. It covers the full software lifecycle, including requirements engineering, architectural design, quality assurance, and modern DevOps practices. The course emphasizes technical trade-offs, scalability, security-by-design, and professional ethics.

The objective is to equip postgraduate students with the ability to manage complex software development projects. This includes moving beyond basic coding to architectural design, systematic testing, and the application of professional engineering standards to ensure maintainable, high-quality software products.

Deep Learning for Natural Language Processing

This course provides an in-depth exploration of modern deep learning techniques for natural language processing (NLP). It covers foundational architectures (RNNs, CNNs), attention mechanisms, transformers, large language models (LLMs), and current research trends. Emphasis is placed on both theoretical understanding and practical implementation, with critical reading of recent research papers.

Machine Learning

Machine learning uses interdisciplinary techniques such as statistics, linear algebra, optimization, and computer science to build computer systems that learn from experience. This course will explain how to build systems that learn and adapt using real-world applications. Some of the topics to be covered include concept learning, neural networks, genetic algorithms, reinforcement learning hidden Markov, deep learning, assessing and comparing, and combining multiple learners and so forth. This course will familiarize students with a broad cross-section of models and algorithms for machine learning, and prepare students for research or industry application of machine learning

By the end of this course, students will be able to:

  • Explain fundamental concepts in machine learning, including the major classes of algorithms, and select and apply appropriate basic algorithms to given problems.
  • Evaluate the performance of machine learning systems using established metrics and techniques.
  • Prepare datasets and implement machine learning methods to achieve specific learning goals within intelligent systems.
  • Assess the suitability of different machine learning paradigms for particular problems and datasets, analyze their capabilities and limitations, and identify potential issues or misleading results.

Apply machine learning algorithms to real-world problems, optimize learned models, and report on the expected accuracy and performance outcomes.

Agile Development Methodologies

This comprehensive course provides an in-depth exploration of agile software development methodologies, focusing on their principles, values, and practical applications. By framing agile within the context of the Agile Manifesto, students will gain a solid understanding of its fundamental philosophy while comparing it to traditional software development approaches like Waterfall and Spiral.

Throughout the course, participants will delve into significant agile methodologies, including Scrum, Kanban, eXtreme Programming (XP), Feature-Driven Development (FDD), and Dynamic Systems Development Method (DSDM). Emphasis will be placed on real-world application through agile practices such as user stories, sprints, and ceremonies, including sprint planning and retrospectives.

Students will also investigate emerging trends in agility, such as DevOps and enterprise agility, and contemplate the broader implications of agility beyond software, encompassing business and research contexts. Through hands-on projects and case studies, participants will develop the skills necessary to implement agile practices effectively and pursue innovative research directions in the field.

Advanced Machine Learning

Course Rationale

Machine learning enables systems to learn from vast data, extract meaningful patterns, and make intelligent, data-driven decisions. It has become a foundational component in various industries such as manufacturing, healthcare, transportation, finance, and energy. This course equips PhD students with the theoretical and practical knowledge necessary for advanced machine learning techniques in real-world problem-solving and research.

Course Objectives and Competences

Upon successful completion of this course, students will be able to:

  • Understand the foundations of deep learning, reinforcement learning, Bayesian inference, and probabilistic models.
  • Design and implement advanced neural network architectures.
  • Apply supervised, unsupervised, and semi-supervised learning methods to diverse domains.
  • Critically evaluate algorithms with respect to performance, scalability, and interpretability.
  • Develop machine learning systems for applications in vision, speech, and natural language.
  • Conduct independent research in emerging areas of machine learning.

Course Description

This course provides a rigorous exploration of advanced topics in machine learning from both mathematical and practical perspectives. Students will learn how to design, train, and optimize deep neural networks (DNNs). Architectures such as CNNs, RNNs, LSTMs, Autoencoders, Transformers, and GANs are explored. Optimization and regularization techniques (SGD, Adam, dropout, batch normalization) are covered alongside probabilistic graphical models and Bayesian approaches. Students gain hands-on experience using frameworks like PyTorch and TensorFlow. Applications include object detection, handwriting analysis, facial recognition, and natural language understanding.

Advanced Natural Language Processing

This course covers a broad range of advanced level topics in natural language processing. It is intended for graduate students in computer science who have familiarity with machine learning fundamentals, but may be new to NLP. It may also be appropriate for computationally sophisticated students in linguistics and related areas. Topics include probabilistic models of language, computationally tractable linguistic representations for syntax and semantics, and selected topics in discourse and text mining. After completing the course, students should be able to read and evaluate current NLP research papers. 

Natural Language Processing

Course Description:

The intent of the course is to present a fairly broad graduate-level introduction to Natural Language Processing (NLP, a.k.a. computational linguistics), the study of computing systems that can process, understand, or communicate in human language. The primary focus of the course will be on understanding various NLP tasks as listed on the course syllabus, algorithms for effectively solving these problems, and methods for evaluating their performance. There will be a focus on statistical and neural-network learning algorithms that train on (annotated) text corpora to automatically acquire the knowledge needed to perform the task. 

Course Objectives:

Upon successful completion of the course, the student will be able to:

  • Understand the basic principles and challenges of natural language processing.
  • Explore the core NLP tasks, such as text preprocessing, language modeling, named entity recognition, and sentiment analysis.
  • Gain hands-on experience in implementing and applying NLP techniques using popular libraries and frameworks.
  • Analyze and critically evaluate the performance and limitations of NLP systems.
  • Understand the ethical considerations and societal implications of NLP technology.

Software Architecture and Design

This course explores software architecture and design principles, practices, and tools. It emphasizes the use of architectural styles, design patterns, and best practices to build scalable, maintainable, and efficient software systems. Students will engage in case studies, discussions, and hands-on projects to develop practical skills.

By the end of this course, students will be able to:

  •        Understand foundational concepts of software architecture and design.
  •        Analyze and apply a variety of architectural styles and patterns.
  •        Use design principles to create high-quality software systems.
  •        Evaluate and document software architectures effectively.
  •        Tackle complex design challenges through collaboration and creativity.