DeepBit 2019 Deep Learning for Bitdefender Engineers

The course is an introduction to up-to-date Deep Learning methods for Bitdefender engineers. It covers very basic theoretical concepts about training neural networks, followed by applications in computer vision and natural language understanding, with accent on building the final project, which was focused on the security field.

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

eagerness to start understanding Deep Learning.

  • Course Team: Stefan Postavaru, Andrei Nicolicioiu, Iulia Duta, Florin Brad, Tudor Berariu, Elena Burceanu, Emanuela Haller, Florin Gogianu

Syllabus

  1. Introduction to Deep Learning
  2. Neural Nets
    • Lab1: PyTorch Intro
    • Assignment1: Sudoku Solver
  3. Optimization
  4. Convolutional NNs
    • Lab2: CNNs on images
    • Assignment2: Count digits in an image
  5. Computer Vision applications
  6. Recurrent NN
    • Lab3: RNNs on Language
    • Assignment3: Predict the programming language of a code snippet
  7. Natural Language Processing applications
  8. PROJECTs status
  9. Poster Session with the PROJECTs
  10. [Bonus] Two lectures on Generative Models

Practical sessions

We use PyTorch for all coding materials and we work in the Colab Notebooks environment. There is a total of three Labs, thress Home Assignments and one final PROJECT - see Poster Session below.

Administrative details

Poster Session

Final Security related PROJECT gave our colleagues the practical experience for applying deep learning in their next security project. See bellow the posters and some photos from the poster session.