Course info

In recent years we witnessed a huge development in machine learning, especially in deep learning which drives a new technological revolution. These models improve searches, apps, social media and open new doors in medicine, automation, self-driving cars, drones and almost all fields of science. In this deep learning class students will learn to work on more advanced deep learning tasks. This lecture is practice focused this year, so students have to work on their project during the whole semester and present their progress in every two week. To apply this course you have to complete the previous machine learning lecture. During the course the students will work on some non-beginner projects, like:

• Time-series data analysis
• Graph-like data
• Object detection
• Image segmentation

Technical details:

• Neptun: deeplea17m
• Language: English

Grading

• The grade will be based on what progress you made and how hard project you chose.

Questions, problems:

• contact us via email: dudas.bence@ttk.elte.hu

Course staff

• Csabai István
• Dudás Bence

PREREQUISITES

• Linear algebra
• Probability and statistics
• Python (numpy, pandas, matplotlib)
• Data Mining and Machine Learning

Reporting

During the semester you have to report your progress in every two week with a 10-15 minutes progression talk. If there are too many students, we meet weekly but only half of the students present. At the end of the semester you have to present a final report, that should be a 30-40 minute.

Materials

• Python for Data Science, Coursera
• CS231n Convolutional Neural Networks for Visual Recognition
• Deep Learning book
• Deep Learning Specialization, Coursera
• An Introduction to Statistical Learning
• Dive into deep learning