Www.p.lodz.pl
Course codeCC5Type and descriptionTCS core curriculum ECTS credit1Course nameComputational Intelligence 1Course name in PolishInteligencja obliczeniowa 1Language of instructionEnglishCourse level8 PRKCourse coordinator dr hab. in?. Artur KlepaczkoCourse instructorsdr hab. in?. Artur Klepaczko, dr hab. in?. prof. P? Piotr SzczypińskiDelivery methods and course durationLectureTutorialsLaboratoryProjectSeminarOtherTotal of teaching hours during semesterContact hours1515E-learningNoNoNoNoNoNoAssessment criteria (weightage)100%Course objectiveThe objective of the course is to learn practical aspects of using machine learning algorithms and data mining methods applied to common engineering problems. Learning outcomesDevelopment trends and research methodology in computational intelligence (W1)Ability to use knowledge, apply methods of computational intelligence (U1) Critical assessment of results produced by the computational intelligence algorithms, validation and verification of outcomes (K1)Assessment methodsUpon completion of the laboratory tasks, students will deliver oral presentation reporting the obtained results. The presentation will be assessed based on completeness (40%), correctness (30%), visual quality of the presentation (15%) and clarity of communication (15%).PrerequisitesFundamentals of statistics and probability theory. Knowledge of Python language or ability to learn it fast independently. Course content with delivery methodsThe course covers the following computational intelligence algorithm:Linear regression classifierSupport vector machineMulti-layer Perceptron networksConvolutional neural networksData modeling using non-linear regression methodsForecasting future values of periodical signals with seasonal trendsThe detailed problems will be explained in the laboratory instructions delivered to students during the laboratory sessions.Acceptance of the laboratory tasks is subject to preparation of the final report in the form of oral presentation presented during the last laboratory session.Basic reference materialsComputer science journals devoted to artificial intelligence and machine learning, e.g.: Artificial Intelligence, Data & Knowledge Engineering, Expert Systems with Applications, Neural Networks, Neurocomputing, IEEE Trans. Pattern Analysis and Machine Intelligence, IEEE Trans. Systems, Man, and Cybernetics, IEEE Trans. Neural Networks.Other reference materialsDocumentation of the Scikit-learn, Prophet, PyTorch and keras librariesAverage student workload outside classroom10 hCommentsLast update2019.04.17 ................
................
In order to avoid copyright disputes, this page is only a partial summary.
To fulfill the demand for quickly locating and searching documents.
It is intelligent file search solution for home and business.