Learning results After the end of the teaching module, the trainee will be able to:
- Identify the representation models and analyze the problem of uncertainty and its forms.
- Recalls basic knowledge about probability distributions and statistical characteristics.
- Describes the simulation process and its applications.
- Import and run model simulation on PC with the Monte Carlo method.
- Explain the concept of optimization and recognize heuristic and genetic search algorithms.
- Define the concept of ignorance and its forms and describe learning methods (supervised, unsupervised, reinforcement).
- Describe the basic modeling process and criteria for selecting models and parameters and define the concept of regression.
- Designs, implements and uses learning algorithms in various scientific fields.
- Representation models, uncertainty, statistics, ambiguity
- Model simulation (Monte Carlo)
- Optimum search (heuristic and genetic algorithms)
- Data, knowledge, model ignorance and learning (supervised or unsupervised and reinforcement)
- Regression (fitting) – Basic modeling
- Simulation, Monte Carlo, fitting applications
Learning results After the end of the teaching module, the trainee will be able to:
- Discusses the purpose and key concepts of machine learning, pattern recognition, artificial intelligence and data quality.
- Define the concept of classification and its various methods, use classification algorithms and evaluate its role in decision making.
- Describes the clustering process and its role in data correlation.
- Describes artificial neural networks, their types and their implementations.
- Recognize the categories of problems and choose the appropriate artificial intelligence method to solve them.
- Designs and implements algorithms to solve problems in various scientific fields.
- Machine Learning – Pattern Recognition and Artificial Intelligence
- Classification (Linear Classification, k-NN, Bayesian, SVM) and decisions
- Clustering (k-means) and correlation
- Neural networks for regression, classification and clustering
- Deep Learning and Convolutional Neural Networks (CNN)
- Modeling problems
- Applications of classification, clustering and neural networks
Learning results After the end of the teaching module, the trainee will be able to:
- Explain the concepts of forecasting and estimation and describe forecasting and estimation models and their characteristics.
- Specifies the use of Kalman and Lainioti filters.
- Defines steady state and steady state Kalman filters.
- Solves the Riccati equation used in steady state Kalman filters.
- Recognizes non-linear prediction and estimation models and the extended Kalman filter.
- Design and program Kalman filters to solve problems in various scientific fields.
- Valuation theory
- Linear Kalman filter
- Steady state
- Linear Lainiotis filter
- Extended Kalman filter (extended Kalman filter)
- Applications