DeepFMI 2020 Learning Deep Neural Networks

  • February 19th: The course takes place in Stoilow lecture hall, every

Wednesday at 16:00 hours. The practicals (only for FMI students) will be every other week, starting the first week, in room 308, from 18:00 hours (right after the lecture).

  • February 7th: The second edition of the course is

about to start (on February 19th). Enroll now!

About

The course is about basic Deep Learning methods, current models and capabilities. It is an optional course primarily (but not exclusively) for third-year undergraduates of the Faculty of Mathematics and Computer Science, University of Bucharest. It covers basic theoretical concepts about training neural networks, followed by applications in computer vision and natural language understanding, with an accent on the applied part, through labs, assignments and the final project.

  • Prerequisites: Basic Python knowledge or several years as a programmer and

eagerness to start understanding Deep Learning.

  • Course Team: Emanuela Haller, Florin Gogianu, Andrei Nicolicioiu, Iulia Duta, Florin Brad, Elena Burceanu, Andrei Manolache, Covaci Adrian

Syllabus

  1. Introduction to Deep Learning
    • Lab1: Intro to Python, PyTorch and Tensors
  2. Neural Nets
  3. Optimization
    • Lab2: Training and Optimization
    • Assignment1
  4. Convolutional Neural Networks
  5. Computer Vision applications
    • Lab3: CNN on images
    • Assignment2: Count digits in an image
  6. Recurrent NN
  7. Natural Language Processing applications
    • Lab4: RNNs on language
  8. Unsupervised Learning Models
  9. PROJECT Status
    • Lab5: Verify Assignments
  10. Poster Session with the PROJECTs

Based on the last year course experience, this second edition will focus less on evaluating the theoretical aspects and will have less payload for the end of the semester. From the lecture content point of view, we will replace the Reinforcement Learning lectures with lectures on Unsupervised Learning.

Practical sessions

We use PyTorch for all coding materials and we work in the Colab Notebooks environment. There is a total of five Labs, two Home Assignments and one final PROJECT, presented in the Poster Session (see below the ones from the Previous Edition).

Administrative details

  • When: February 19th - April 22nd 2020, on Wednesday evening
  • Where: Faculty of Mathematics and Computer Science, University of Bucharest
  • Google Group: deeplearning_fmi_2020
  • Enroll now: Registration is necessary only if you did not choose this optional already. Places are limited, first come first served rule will be applied. The exact room and time will be provided via email.

Previous Edition

You can find below the posters from the previous edition and full course details DeepFMI 2019: