. "Artificial Intelligence"@en . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . "Introduction to deep learning"@en . . "6" . "The course provides an introduction to key concepts, architectures, and algorithms for Deep Learning and its applications. It covers the following topics:\r\n\r\nPart One: Multilayer Peceptron and Backpropagation\r\n\r\nFrom a Single Layer Perceptron to Deep Learning: a historical perspective\r\nAlgorithms for training MLPs: Stochastic Gradient Descent and its variants; Backpropagation\r\nAlternative activation and loss functions; Initialization, Regularization, Dropout, Batch Normalization\r\nIntroduction to GPU-computing, Keras, TensorFlow; Hyperparameter Tuning\r\n\r\nPart Two: Deep Learning for computer vision and language processing\r\n\r\nConvolutional Networks: key architectures and applications; Transfer Learning\r\nRecurrent Networks: from Backpropagation Through Time to Attention Mechanism and Transformers\r\n\r\nPart Three: Generative Networks\r\n\r\nAutoencoders\r\nGenerative Adversarial Networks (GAN's)\r\nDiffusion Models\r\n\r\nDuring the course several state-of-the-art applications of Deep Learning to image recognition, computer vision, language modeling, game playing programs, etc., will be discussed. The course consists of weekly lectures, three programming assignments (in Python, TensorFlow) and the final written exam.\n\nOutcome: Not Provided" . . "Presential"@en . "TRUE" . . "Seminar advances in deep learning"@en . . "6" . "In recent years we have witnessed an explosion of research, development, and applications of Deep Learning. The main objective of this course is to provide a wide overview of the current state of this area and to focus on a few, carefully selected topics, covering them in depth by studying and presenting most relevant papers, and doing own research on these selected topics. This research will have a form of producing new experimental results, testing new algorithms or theories and documenting findings in scientific reports. The best reports can be submitted to conferences or published as research papers.\r\n\r\nDuring the course students will work (in small teams) on selected topics/problems, performing experiments on GPU-computers, reporting on their progress during weekly meetings. Each team will have to summarize their work in a final presentation and a project report.\n\nOutcome:\nDuring the course students will:\r\n\r\ngain an overall picture of the recent developments in Deep Learning,\r\nidentify some promising research directions,\r\ngain some hands-on research experience, including studying related papers, identifying research problems, inventing solutions of these problems, verifying their ideas by experimenting and documenting findings in a scientific style,\r\nlearn to work together is small research teams,\r\nlearn to prepare and give presentations,\r\nlearn to write scientific reports." . . "Presential"@en . "TRUE" . . "Deep learning"@en . . "8" . "The course aims at teaching the required skills to \r\nuse deep learning methods on applied problems. \r\nIt will show how to design and train a deep \r\nneural network for a given task, and the sufficient \r\ntheoretical basis to go beyond the topics directly \r\nseen in the course. The planned content of \r\nthe course:\r\n• What is deep learning, introduction to tensors.\r\n• Basic machine-learning, empirical risk \r\nminimization, simple embeddings.\r\n• Linear separability, multi-layer perceptrons, \r\nback-prop.\r\n• Generalized networks, autograd, batch processing, \r\nconvolutional networks.\r\n• Initialization, optimization, and regularization.\r\nDrop-out, activation normalization, skip \r\nconnections.\r\n• Deep models for Computer Vision.\r\n• Analysis of deep models.\r\n• Auto-encoders, embeddings, and generative models.\r\n• Deep learning for sequences - Recurrent neural \r\nnetworks (RNNs); vanishing and exploding \r\ngradients; Long Short-Term Memory (LSTM); \r\ndeep RNNs; bidirectional RNNs; combination of \r\nCNNs with RNNs - pytorch tensors, deep learning \r\nmodules, and internals.\n\nOutcome: Not Provided" . . "Presential"@en . "TRUE" . . "Application of artificial intelligence in big data technologies"@en . . "3" . "Attention is being paid to basic artificial intelligence domains – search, representation, \nuncertainty. Discussed are approaches, techniques, representation techniques and basic \nalgorithms. Besides classical algorithms search topic considers heuristics and \napproximation as modelling strategies. The representation topic covers constraint \nsatisfaction, logical formalism and effective algorithms for logical inference. The \nuncertainty topic refers to probabilistic inference, formalisms for decision processes and \napproaches for uncertainty modeling. Algorithms used in practical artificial intelligence are\npresented. Application of investigated artificial intelligence models in natural language \nprocessing, vision, machine learning and robotics is discussed. \n\nOutcome:\nEquipped with theoretical knowledge and practical skills the students will be able to select the \nalgorithm that fits best for inference in a specific domain; to implement and tune artificial \nintelligence algorithms; to select the appropriate representation of artificial intelligence \nproblem or domain model, as well as to design models with desired representation." . . "Presential"@en . "FALSE" . . "Introduction to machine learning"@en . . "6.7" . "The goal of this course is to provide an accelerated preparation for the more advanced courses in the Michaelmas term. This preparation includes several foundational topics in machine learning and through these we cover essential mathematical background and optimisation tools.\r\n\r\nAims:\r\n\r\nProvide a thorough introduction into the topic of statistical inference including maximum-likelihood and Bayesian approaches. Introduce important tools from probability and statistics.\r\nIntroduce algorithms for regression, classification, clustering and sequence modelling. Through these use mathematical tools including linear algebra, eigenvectors and eigenvalues, multidimensional calculus, and calculus of variations. \r\nIntroduce basic concepts in optimisation and dynamic programming, including gradient ascent and belief propagation. \n\r\nObjectives:\r\n\r\nUnderstand the use of maximum-likelihood and Bayesian inference and the strengths and weaknesses of both approaches. \r\nImplement methods to solve simple regression, classification, clustering and sequence modelling problems. \r\nImplement simple optimisation methods (gradient and coordinate descent, EM) and dynamic programming (Kalman filter or Viterbi decoding). \n\nOutcome: Not Provided" . . "Presential"@en . "TRUE" . . "Computer vision"@en . . "6.7" . "Aims\r\n\r\nThe aims of the course are to:\r\n\r\nintroduce the principles, models and applications of computer vision;\r\ncover image structure, projection, stereo vision, structure from motion and object detection and recognition;\r\ngive case studies of industrial (robotic) applications of computer vision, including visual navigation for autonomous robots, robot hand-eye coordination and novel man-machine interfaces.\n\nOutcome:\nAs specific objectives, by the end of the course students should be able to:\r\n\r\ndesign feature detectors to detect, localise and track image features;\r\nmodel perspective image formation and calibrate single and multiple camera systems;\r\nrecover 3D position and shape information from arbitrary viewpoints;\r\nappreciate the problems in finding corresponding features in different viewpoints;\r\nanalyse visual motion to recover scene structure and viewer motion, and understand how this information can be used in navigation;\r\nunderstand how simple object recognition systems can be designed so that they are independent of lighting and camera viewpoint;\r\nappreciate the industrial potential of computer vision but understand the limitations of current methods.\r\nLectures for this course are shared with 4th year Engineering undergraduates." . . "Presential"@en . "TRUE" . . "Deep learning & structured data"@en . . "6.7" . "Aims\r\nThe aims of the course are to:\r\n\r\nteach the basic concepts of deep learning and forms of structure that can be used for generative and discriminative models. In addition, the use of models for classifying structured data, such as speech and language, will be discussed\n\nOutcome:\nObjectives\r\nAs specific objectives, by the end of the course students should be able to:\r\n\r\nunderstand the basic principles of pattern classification and deep learning;\r\nunderstand generative and discriminative models for structured data;\r\nunderstand the application of deep-learning to structured data;\r\napply pattern processing techniques to practical applications.\r\n* This module is shared with 4th Year undergraduates from the Department of Engineering." . . "Presential"@en . "TRUE" . . "Probabilistic machine learning"@en . . "6.7" . "Aims\r\n \r\nThe aim of the course is to:\r\nintroduce students to basic concepts in machine learning, focusing on statistical methods for supervised and unsupervised learning.\n\nOutcome:\nObjectives\r\n \r\nBy the end of the course students should be able to:\r\ndemonstrate a good understanding of basic concepts in statistical machine learning;\r\napply basic machine learning methods to practical problems.\r\n \r\nThis module is shared with 4th year undergraduate students from the Department of Engineering." . . "Presential"@en . "TRUE" . . "Advanced machine learning"@en . . "5" . "Aims\r\n\r\nThe aim of this module is to teach advanced topics that will enable students to follow state-of-the-art research in machine learning.\n\nOutcome:\nOn completion of this module, students should:\r\n\r\nunderstand advanced topics in machine learning;\r\nbe able to read current research papers in the field\r\nbe able to implement state of the art learning algorithms\r\nbe ready to conduct research in the field." . . "Presential"@en . "TRUE" . . "Machine learning and the physical world"@en . . "5" . "Aims\r\n\r\nThe module “Machine Learning and the Physical World” is focused on machine learning systems that interact directly with the real world. Building artificial systems that interact with the physical world have significantly different challenges compared to the purely digital domain. In the real world data is scares, often uncertain and decisions can have costly and irreversible consequences. However, we also have the benefit of centuries of scientific knowledge that we can draw from. This module will provide the methodological background to machine learning applied in this scenario. We will study how we can build models with a principled treatment of uncertainty, allowing us to leverage prior knowledge and provide decisions that can be interrogated.\r\n\r\nThere are three principle points about machine learning in the real world that will concern us.\r\n\r\nWe often have a mechanistic understanding of the real world which we should be able to bootstrap to make decisions. For example, equations from physics or an understanding of economics.\r\nReal world decisions have consequences which may have costs, and often these cost functions need to be assimilated into our machine learning system.\r\nThe real world is surprising, it does things that you do not expect and accounting for these challenges requires us to build more robust and or interpretable systems.\r\nDecision making in the real world hasn’t begun only with the advent of machine learning technologies. There are other domains which take these areas seriously, physics, environmental scientists, econometricians, statisticians, operational researchers. This course identifies how machine learning can contribute and become a tool within these fields. It will equip you with an understanding of methodologies based on uncertainty and decision making functions for delivering on these challenges.\n\nOutcome:\nYou will gain detailed knowledge of\r\n\r\nsurrogate models and uncertainty\r\nsurrogate-based optimization\r\nsensitivity analysis\r\nexperimental design\r\nYou will gain knowledge of\r\n\r\ncounterfactual analysis\r\nsurrogate-based quadrature\r\n* Lectures take place in the Department of Computer Science and Technology and are part of the MPhil in Advanced Computer Science." . . "Presential"@en . "FALSE" . . "Artificial intelligence and knowledge base"@en . . "7.5" . "Introduction to Technical Intelligence. Categories of technical intelligence, supervised, unsupervised and semi-supervised learning methods. Methods with or without modeling. Probabilistic methods. Intelligent agents.\r\nIntroduction to artificial intelligence methods without modeling (stateless - Supervised learning). The structure of the simple preceptor, neuron. The structure of neural networks. The method of backpropagation. Syneclectic deep learning neural networks. Nonlinear categorization methods.\r\nIntroduction to artificial intelligence methods without modeling (stateless). Classification methods, k-means, DBSCAN, spectral clustering. Unsupervised learning methods using training (autoencoders, stacked autoencoders, deep learning).\r\nIntroduction to artificial intelligence methods with modeling (state modeling - deterministic). Introduction to Search Problem Modeling. Search trees. Heuristic methods. Local Search Algorithms and Optimization Methods. Search by width, depth. Uniform Cost Search. A Star A Star Relaxations.\r\nIntroduction to artificial intelligence methods with state modeling. Competitive methods. Game Theory, Max Min Algorithms, ExpectMax Algorithms, Alpha-Beta pruning. Adversarial Generative Networks (GANs) and deep learning\r\nIntroduction to artificial intelligence methods with state modeling. Bayesian classifiers, Decision tress, modeling with Markov models, policy evaluation, particle filters, Q-learning, Reinforcement learning, deep reinforcement learning\r\nIntroduction to Knowledge Bases and Expert Systems. Symbolic representation of knowledge: objects, production rules, semantic networks, frameworks, tables.\r\nSymbolic Inference Methods and Decision Control Procedures. Use and mechanism of production rules, correct, reverse and two-way reasoning, deep – and broad – research.\r\nRepresentation and drawing conclusions with uncertain and inconclusive knowledge. Uncertain Reasoning, Fuzzy Logic, Probability Reasoning, Theory of Testimony.\r\nDevelopment of experienced systems. The Architecture of Experienced Systems. Steps to Develop an Expert System. Formulation and Identification of the Problem. Conceptual Conception of the Problem, Capture of knowledge from written sources and Experts. Standardization and Organization of the Knowledge Base, Implementation of the Expert System, Evaluation of the Expert System.\r\nProgramming Languages and Expert Systems Development Tools. Types of Tools, Language or Tool Selection, Hardware Infrastructure for Expert Systems.\r\nExamples of expert systems. Review of systems experiences in Earth Sciences.\n\nOutcome: Not Provided" . . "Presential"@en . "TRUE" . . "Machine learning"@en . . "4" . "The course is a mixture of lectures, workshops, and a practical project.The lectures will focus on introducing the fundamental concepts of machine learning whereas the workshops will interactively demonstrate these concepts. The students will also undertake a practical project to deepen their understanding and gain hands-on experience. This project will have space-related objectives and the realization will be team-based.\n\nOutcome:\n– Learn the foundations of machine learning;- Learn the foundations of evolutionary computation;- Learn the foundations of deep learning and artificial neural networks;- Familiarize with applications of machine learning in space-related problems." . . "Presential"@en . "TRUE" . . "Applied machine learning"@en . . "6" . "The course objective is to give to the student a general idea on how to develop a machine learning system. The course will cover aspects related to the model architecture, data collection and processing, until the deployment of the system. At the end of the course, the student is expected to be able to evaluate the feasibility of a simple machine learning project and he will be able to manage it deployment in all its phases. Theoretical lectures will be alternated with hands-on exercises in python." . . "Presential"@en . "FALSE" . . "Artificial intelligence and data processing"@en . . "5" . "Learning outcomes of the course unit:\nBy completion of the subject Artificial Intelligence and Data Processing, a student gains knowledge on artificial intelligence, the theory and applications of machine learning and data processing. The subject offers systematic approach to the best known methods of machine learning, especially neural networks. Methods of signal processing, analysis and recognition are systematically studied. Course Contents:\n1D and 2D data processing and analysis in time and frequency domain, convolution, Fourier transform, filtering, image reconstruction.\nPattern recognition.\nPrinciples of artificial intelligence, machine learning, and neural networks.\nConventional and deep neural network architectures and learning.\nkernel methods, support vector machines, clustering, conventional and deep neural networks and learning." . . "Presential"@en . "TRUE" . . "Introduction to machine learning"@en . . "5" . "Description and learning outcomes are not available." . . "Presential"@en . "FALSE" . . "Machine learning for the built environment"@en . . "5" . "This is an introductory course for machine learning to equip students with the basic knowledge and skills for further study and research of machine learning. It introduces the theory/methods of well-established machine learning and state-of-the-art deep learning techniques for processing geospatial data (e.g., point clouds). The students will also gain hands-on experiences by applying commonly used machine learning techniques to solve practical problems through a series of lab exercises and assignments. \n\nAfter the course, the students will be able to:\r\n- explain the impact, limits, and dangers of machine learning; give use cases of machine learning for the built environment;\r\n- explain the main concepts in machine learning (e.g., regression, classification, unsupervised learning, supervised learning, overfitting, training, validation, cross-validation, learning curve);\r\n- explain the principles of well-established unsupervised and supervised machine learning techniques (e.g., clustering, linear regression, Bayesian classification, logistic regression, SVM, decision tree, random forest, and neural networks);\r\n- preprocess data (e.g., labelling, feature design, feature selection, train-test split) for applying machine learning techniques;\r\n- select and apply the appropriate machine learning method for a specific geospatial data processing task (e.g., object classification);\r\n- evaluate the performance of machine learning models." . . "Presential"@en . "FALSE" . . "Computer vision & machine learning"@en . . "5" . "no data" . . "Presential"@en . "TRUE" . . "Transitional work on machine learning in smart environment"@en . . "no data" . "N.A." . . "Presential"@en . "TRUE" . . "Machine learning"@en . . "6" . "Machine learning language environments (PyTorch, TensorFlow, Keras, SciKit-Learn,\nNumPy). Linear and nonlinear regression, polynomial curve fitting, and classification. Bias-\nvariance trade-off. Radial basis functions. Neural networks. Activation functions, optimization\nalgorithms. Cross-validation, regularization, bootstrap. Convolutional neural networks and\nvisual data analysis. Batch-normalization, Dropout. Pre-trained models. Transfer learning.\nDetection of the objects by U-Net type networks. Recurrent neural networks in series\nanalyses. Generative adversarial neural networks." . . "Presential"@en . "FALSE" . . "Principles of artificial intelligence"@en . . "6" . "no data" . . "Presential"@en . "TRUE" . . "3d computer vision"@en . . "6" . "no data" . . "Presential"@en . "FALSE" . . "Machine learning"@en . . "6" . "no data" . . "Presential"@en . "FALSE" . . "Computer vision p"@en . . "5" . "no data" . . "Presential"@en . "FALSE" . . "Computer vision p"@en . . "5" . "no data" . . "Presential"@en . "FALSE" . . "Applied deep learning"@en . . "2" . "The aim of this course is to provide an overview of modern applications of machine learning and develop practical skills in using deep neural networks for common machine learning tasks. The objective of this course is to provide an introduction into artificial neural network based models, as well as an introduction to existing API frameworks for training such models. Previous knowledge regarding machine learning is not expected. The practical assignments will be developed in Python programming language.\r\nThe language of instruction is Latvian.\r\nResults\tKnowledge: 1. Describe the main neural network machine learning approaches. (EQUANIE concepts E1-1, E-12) Skills: 2. Independently develop software systems with deep learning solutions. (EQUANIE realization E3-5, practice E5-1) Competencies: 3. Provide examples of suitable applications for machine learning methods and their limitations. (EQUANIE concepts E1-4, analysis E2-1)\r\n4. Evaluate practical problems which may require machine learning and propose the appropriate methods to solve them. (EQUANIE analysis E2-3, E2-4)" . . "Presential"@en . "FALSE" . . "Statistical foundations of machine learning"@en . . "6" . "In this course, we Introduce the basics of Machine Learning from a statistical perspective. The focus of this course is on supervised learning, but other learning paradigms are also studied. The following topics will be addressed:\n\n1. The Learning Problem - 2. Is Learning Feasible? - 3. The Linear Model - 4. Error and Noise - 5. Training versus Testing - 6. Theory of Generalization - 7. The Vapnik-Chervonenkis Dimension - 8. Bias-Variance Tradeoff - 9. Neural Networks - 10. Overfitting - 11. Regularization - 12. Validation - 13. Support Vector Machines - 14. Kernel Methods - 15. Bayesian learning - 16. Reinforcement learning.\nGENERAL COMPETENCIES\r\nIntroduce the basics of Machine Learning from a statistical perspective. The student has to be able to 1) understand machine learning techniques, 2) formally prove theoretical guarantees about machine learning, 3) implement these techniques in Python, 4) apply these techniques to benchmark and real-world problems, and 5) evaluate the performance of machine learning techniques.\r\n\r\n• Knowledge and insight: After successful completion of the course the student should have insight into which problems can benefit from machine learning techniques and how to apply these techniques to the problem at hand. The student will gain insight in the studied methodologies and be able to reason about model complexities and learning guarantees.\r\n\r\n• Use of knowledge and insight: The student should be able to apply machine learning techniques and to tune the parameters of the chosen algorithm. The use of python will enable the student to write programs to solve problems. The exercise sessions and practical exam project will challenge students to solve research questions that consider both synthetic and real-world data.\r\n\r\n• Judgement ability: The student should be able to judge the qualities of the different machine learning techniques and their results on the problem at hand.\r\n\r\n• Communication: The student should be able to communicate with experts about machine learning problems. The student should also be able to report and to present the results of his or her experiments to both specialists and non-specialists. The practical exam project will challenge students to collaborate with their peers and communicate their results effectively." . . "Presential"@en . "FALSE" . . "Deep learning"@en . . "5" . "Machine perception of natural signals has improved a lot in the recent years thanks to deep learning (DL). Improved image recognition with DL will make self-driving cars possible and is leading to more accurate image-based medical diagnosis. Improved speech recognition and natural language processing with DL will lead to many new intelligent applications within health-care and IT. Pattern recognition with DL in large datasets will give new tools for drug discovery, condition monitoring and many other data-driven applications.\r\n\r\nThe purpose of this course is to give the student a detailed understanding of the deep artificial neural network models, their training, computational frameworks for deployment on fast graphical processing units, their limitations and how to formulate learning in a diverse range of settings. These settings include classification, regression, sequences and other types of structured input and outputs and for reasoning in complex environments." . . "Presential"@en . "FALSE" . . "Inverse problems and machine learning in earth and space physics"@en . . "5" . "This course covers advanced methods for inversion of geophysical and astrophysical data, including machine learning techniques. Case studies from a wide range of inverse problems in Earth and Space physics (e.g. seismic tomography, geomagnetism, exoplanets, ground penetrating radar, galactic emission spectra, gravity) are presented and solved. The emphasis in this course is on inversion methods that handle non-Gaussian noise and use of suitable a priori information to get the most out of the observed data.\n\nPython will be used as a tool throughout the course." . . "Presential"@en . "FALSE" . . "Machine learning with python"@en . . "5.00" . "The objective of this module is to familiarise students with the fundamental theoretical concepts in machine learning, as well as to instruct students in the practical aspects of applying machine learning algorithms. Key techniques in supervised machine learning will be covered, such as classification using decision trees and nearest neighbour algorithms, and regression analysis. A particular emphasis will be placed on the evaluation of the performance of these algorithms. In unsupervised machine learning, a number of popular clustering algorithms will be presented in detail. Further topics covered include ensemble learning, dimension reduction, and model selection. This module requires strong mathematical ability, as some of the algorithms require some understanding of linear algebra and statistical concepts. Exercises and assignments will use the machine learning libraries in Python.\n\nLearning Outcomes:\nOn completion of this module, students will be able to:\n1) Distinguish between the different categories of machine learning algorithms;\n2) Identify a suitable machine learning algorithm for a given application or task;\n3) Run and evaluate the performance of a range of algorithms on real datasets using Python libraries." . . "Presential"@en . "FALSE" . . "Machine learning with python (online)"@en . . "5.00" . "The objective of this module is to familiarise students with the fundamental theoretical concepts in machine learning, as well as to instruct students in the practical aspects of applying machine learning algorithms. Key techniques in supervised machine learning will be covered, such as classification using decision trees and nearest neighbour algorithms, and regression analysis. A particular emphasis will be placed on the evaluation of the performance of these algorithms. In unsupervised machine learning, a number of popular clustering algorithms will be presented in detail. Further topics covered include ensemble learning, dimension reduction and model selection. This module requires strong mathematical ability, as some of the algorithms require some understanding of linear algebra and statistical concepts. Exercises and assignments will use the machine learning libraries in Python.\n\nLearning Outcomes:\nOn completion of this module, students will be able to:\n1) Distinguish between the different categories of machine learning algorithms;\n2) Identify a suitable machine learning algorithm for a given application or task;\n3) Run and evaluate the performance of a range of algorithms on real datasets using Python libraries." . . "Online"@en . "FALSE" . . "Deep learning"@en . . "5.00" . "no data" . . "Presential"@en . "FALSE" . . "Artificial intelligence"@en . . "6" . "understand the different machine learning problems and methods;\n design for a given data analytics problem the appropriate solution to be used;\n implement deep learning models within a standard framework." . . "Presential"@en . "TRUE" . . "Computer vision"@en . . "6" . "understand advanced models and techniques for image processing;\n solve realistic problems in computer vision." . . "Presential"@en . "TRUE" . . "Advanced concepts in machine learning"@en . . "6.0" . "This course will introduce a number of advanced concepts in the field of machine learning such as Support Vector Machines, Gaussian Processes, Deep Neural Networks, etc. All of these are approached from the view that the right data representation is imperative for machine learning solutions. Additionally, different knowledge representation formats used in machine learning are introduced. This course counts on the fact that basics of machine learning were introduced in other courses so that it can focus on more recent developments and state of the art in machine learning research. Labs and assignments will give the students the opportunity to implement or work with these techniques and will require them to read and understand published scientific papers from recent Machine Learning conferences.\n\nPrerequisites\nDesired Prior Knowledge: Machine Learning\n\nRecommended reading\nPattern Recognition and Machine Learning - C.M. Bishop; Bayesian Reasoning and Machine Learning - D. Barber; Gaussian Processes for Machine Learning - C.E. Rasmussen & C. Williams; The Elements of Statistical Learning - T. Hastie et al.\n\nMore information at: https://curriculum.maastrichtuniversity.nl/meta/465009/advanced-concepts-machine-learning" . . "Presential"@en . "FALSE" . . "Computer vision"@en . . "6.0" . "Can we make machines look, understand and interpret the world around them? Can we make cars that can autonomously navigate in the world, robots that can recognize and grasp objects and, ultimately, recognize humans and communicate with them? How do search engines index and retrieve billions of images? This course will provide the knowledge and skills that are fundamental to core vision tasks of one of the fastest growing fields in academia and industry: visual computing. Topics include introduction to fundamental problems of computer vision, mathematical models and computational methodologies for their solution, implementation of real-life applications and experimentation with various techniques in the field of scene analysis and understanding. In particular, after a recap of basic image analysis tools (enhancement, restoration, color spaces, edge detection), students will learn about feature detectors and trackers, fitting, image geometric transformation and mosaicing techniques, texture analysis and classification using unsupervised techniques, face analysis, deep learning based object classification, detection and tracking, camera models, epipolar geometry and 3D reconstruction from 2D views.\n\nPrerequisites\nNone.\n\nDesired prior knowledge: Basic knowledge of Python, linear algebra and machine learning. This course offers the basics on image processing although prior knowledge is also a plus.\n\nRecommended reading\n“Digital Image Processing”, Rafael C. Gonzalez & Richard E. Woods, Addison-Wesley, “Computer Vision: Models, Learning and Inference”, Simon J.D. Prince 2012.\n\nMore information at: https://curriculum.maastrichtuniversity.nl/meta/466719/computer-vision" . . "Presential"@en . "FALSE" . . "Artificial intelligence I"@en . . "6.0" . "General objectives:\n\nAcquire the basic principles of the field of Artificial Intelligence, specifically the modeling of intelligent systems through the notion of intelligent agent.\nAcquire the basic techniques developed in the field of Artificial Intelligence, concerning symbol manipulation and, more speicifically, discrete models.\n\nSpecific objectives:\n\nKnowledge and understanding:\n\nAutomated search in the space state: general methods, heuristic driven methods, local Search. Factored representations: constraint satisfaction problems, automated planning.\nKnowledge Representation through formal systems: propositional logic, first order logic, description logic (hints), non monotonic reasoning (hints). Usage of logic as a programming language: PROLOG.\n\nApplying knowledge and understanding:\n\nModeling problems by means of the manifold representation techniques acquired through the course. Analysis of the behavior of the basic algorithms for automated reasoning.\n\nMaking judgements:\nBeing able to evaluate the quality of a representation model for a problem and the results of the application of the reasoning algorithms when run on it.\n\nCommunication:\nThe oral communication skills are stimulated through the interaction during class, while the writing skills will be developed thorugh the analysis of exercises and answers to open questions, that are included in the final test.\n\nLifelong learning skills:\nIn addition to the learning capabilities arising from the study of the theoretical models presented in the course, the problem solving capabilities of the student will be improved through the exercises where the acquired knowledge is applied." . . "Presential"@en . "TRUE" .