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 introductory deep learning class students will learn about neural networks, objectives, optimization algorithms and different architectures. During the semester students will work on two projects, where students try out different algorithms and architectures. To successfully complete the class, prior knowledge in Python (numpy, pandas, matplotlib) is required. During the course the students will learn about and will get comfortable with popular deep learning frameworks.

Technical details:

• Neptun: deeplea17m
• Language: Hungarian (slides and the materials in English)

Grading

• 2 Kaggle competitions during the semester
• predefined points with thresholds
  • above minimal baseline: 2 point
  • above baseline: 3 points
  • being in the top 50% of solutions: 4 points
• extra points could be awarded for a high-quality report
  • the maximal reward / report: 1 point
• your grade will be the sum of your points
  • the ideal point range should in the range (4, 10]
  • grading:
    • [5.0, 6.): 2
    • [6., 7.]: 3
    • [7., 8.): 4
    • [8., 10.]: 5
• if you are not content with you grade after the end YOU CAN APPLY FOR AN ORAL EXAM
  • you cannot get a worse grade
  • no topics, any question could be asked from the lectures

1st Kaggle competition

Early availability of challanges, they could still be modified.

• Introduction to ML - ACE2 binding prediction

2nd Kaggle competition

Early availability of challanges, they could still be modified.

• Introduction to DL - OCR challenge

Questions, problems:

• contact us via email: olar.alex@ttk.elte.hu

Course staff

• Biricz András
• Bedőházi Zsolt
• Kilim Oz
• Olar Alex
• Csabai István

SYLLABUS

parts	topics	instructor	materials	date
I.	Introduction to machine learning	Olar Alex	notebooks: 1, 2, 3, 4, 5, 6, slide	2023. 03. 14.
II.	Introduction to deep learning	Olar Alex	notebooks: 1, 2, slide	2023. 04. 18.
III.	Deeper dive into deep learning	Olar Alex	slide	2023.05.23.

PREREQUISITES

• Linear algebra
• Probability and statistics
• Python (numpy, pandas, matplotlib)

Reporting

During the semester there will be two Kaggle in-class challenges with written reports after each of them. Report outline.

• your grade will be the sum of your points
  • the ideal point range should in the range (4, 10]
  • grading:
    • [5.0, 6.): 2
    • [6., 7.]: 3
    • [7., 8.): 4
    • [8., 10.]: 5

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