After an introduction to the fundamental algorithms of Artificial Intelligence (AI), it will be shown how AI is a powerful ally in engineering design. Different transversal applications of Engineering will be studied and investigated: from the resolution and optimization of mathematical models and physical systems, to the analysis and classification of data. At the end of the course, students will be able to use AI techniques even without using specific libraries or software.
teacher profile teaching materials
Numerical modeling and use of computers in scientific computing
Artificial neural networks: the multilayer perceptron (MLP)
Interpolation and approximation with neural networks (linear and non-linear regression), graphic example also in 3D
Supervised training: backpropagation algorithm for calculating the gradient of the error function of an MLP
Introduction to optimization: training algorithms
Convolutional Neural Networks (CNN)
Recursive Neural Networks (RNN)
Unsupervised training
Reinforcement training
Generative neural networks
Genetic algorithms
Swarm intelligence
Development of source codes in C/C++ as libraries for Matlab and Python
Application examples:
Simulation of a solar cell with neural networks
Neural networks for solar panel optimization
Neural solarimeter
Resolution of thermal circuits
Calculation of the parameters of the static Jiles – Atherton model
Calculation of the parameters of the one-diode model of a solar cell
https://d2l.ai/
Programme
Introduction to Artificial IntelligenceNumerical modeling and use of computers in scientific computing
Artificial neural networks: the multilayer perceptron (MLP)
Interpolation and approximation with neural networks (linear and non-linear regression), graphic example also in 3D
Supervised training: backpropagation algorithm for calculating the gradient of the error function of an MLP
Introduction to optimization: training algorithms
Convolutional Neural Networks (CNN)
Recursive Neural Networks (RNN)
Unsupervised training
Reinforcement training
Generative neural networks
Genetic algorithms
Swarm intelligence
Development of source codes in C/C++ as libraries for Matlab and Python
Application examples:
Simulation of a solar cell with neural networks
Neural networks for solar panel optimization
Neural solarimeter
Resolution of thermal circuits
Calculation of the parameters of the static Jiles – Atherton model
Calculation of the parameters of the one-diode model of a solar cell
Core Documentation
Dive into deep learninghttps://d2l.ai/
Reference Bibliography
Dive into deep learning https://d2l.ai/Attendance
Optional but highly recommended attendance.Type of evaluation
Design and implementation of a machine learning model