Course title:
Artificial Inteligence in Data Science
Primary programme:
Fizikus mérnök BSc
ECTS credits:
5
Course type:
compulsory
Number of lectures per week:
1
Number of practices per week:
2
Number of laboratory exercises per week:
0
Further knowledge transfer methods:
Grading:
Coursework grade
Special grading methods:
Home and project works
Semester:
7
Prerequisites:
Introduction to Numerical Algorithms
Responsible lecturer:
Dr. János Török, associate professor, PhD
Lecturers and instructors:
Course description:
Study and application to data the different types of machine learning methods
Subjects:
Basic image processing
Threshold methods, Otsu threshold
K-means clustering
Segmentation
Pattern matching
Feedforward neural networks
Backpropagation
Convolutional neural networks
Recurrent neural networks , LSTM networks
Transfer learning
Reinforcement learning
Applications:
Number recognition
Backpropagation implemented with matrix operations
Neural network frameworks (scikit-learn, keras, tensorflow, pytorch)
Temporal prediction
Text analysis, word gram
learning games, Q-learning
Reading materials:
Michelucci, Umberto. Advanced applied deep learning: convolutional neural networks and object detection. Apress, 2019. ISBN-13: 978-1484249758
Ian Goodfellow and Yoshua Bengio and Aaron Courville, Deep Learning, MIT Press, 2016, https://www.deeplearningbook.org/
https://keras.io/getting_started/intro_to_keras_for_researchers/
List of competences:
Please find the detailed list, as quoted from the Hungarian training and outcome requirements of the Physicist Engineer program, in the Hungarian version of the course description.