Deep Learning & Applied AI

Teaching material for the course of Deep Learning and Applied AI, 2nd semester 2020, Sapienza University of Rome

Deep Learning & Applied AI

Course material

News

  • 24/08/2020: Exam dates for September are in the following date ranges: 01-04 Sep, 07-11 Sep, and 14-17 Sep. Please register on infostud for the date range you wish to take the exam, and contact the Professor to set a specific time and date.

  • 07/05/2020: Please fill out the OPIS questionnaire; the OPIS code for this course is LNKUH8AA. Click here for instructions.

Logistics

Lecturer: Prof. Emanuele Rodolà

Assistants: Dr. Luca Moschella, Dr. Antonio Norelli

When: Mondays 16:00–19:00 and Wednesdays 08:00–10:00 (official schedule)

Where: Aula Alfa, via Salaria 113

Office Hours: By appointment, contact Prof. Rodolà

Pre-requisites

Programming fundamentals in Python; calculus; linear algebra.

Textbook and reading material

Due to the ever-evolving nature of the topic, there is no fixed textbook as a reference. Specific material in the form of scientific articles and book chapters will be given throughout the lectures.

Grading

Project + oral examination.

The project must follow one of these formats:

  • survey on a topic
  • reproduction of a scientific article + your own extra contribution
  • original contribution

The oral examination covers the entire program, not just the project!

Please register on Infostud, and contact the Professor to fix a specific day and time.

Lectures

For all the code in one place, visit the tutorial page.

Note on the videos: Youtube subtitles seem to work quite well. If you find the recorded voice a bit too muffled, turning on the subtitles should help. Incidentally, this also gives you quasi-course notes for free.

Date Topic Reading Code & Data
       
Mon 24 Feb Introduction slides  
       
Wed 26 Feb Data, features, and embeddings slides  
       
Mon 02 Mar Recap of linear algebra slides  
       
Wed 04 Mar [Code] Tensors notebook Open In Colab
       
Mon 09 Mar Linear regression, convexity, and gradients slides ; video  
       
Wed 11 Mar Matrix meta-mechanics ; [Code] Tensor operations slides ; video ; notebook Open In Colab
       
Mon 16 Mar Going nonlinear, overfitting, and regularization slides ; video  
       
Wed 18 Mar [Code] Linear models & PyTorch datasets notebook Open In Colab
       
Mon 23 Mar Stochastic gradient descent slides ; video 2D gradient demo (Matlab)
       
Wed 25 Mar [Code] Logistic regression and optimization notebook Open In Colab
       
Mon 30 Mar Multi-layer perceptron and back-propagation slides ; video  
       
Wed 01 Apr [Code] Autograd and modules notebook Open In Colab
       
Mon 06 Apr Convolutional neural networks slides ; video  
       
Wed 08 Apr Q&A ; [Code] Convolutional neural networks Q&A chat ; Q&A video ; notebook Open In Colab
       
Wed 15 Apr Regularization slides ; video  
       
Wed 22 Apr Projects slides ; video  
       
Wed 29 Apr [Code] Uncertainty, regularization and the deep learning toolset notebook Open In Colab
       
Mon 04 May Deep generative models slides ; video - p1 ; video - p2  
       
Wed 06 May [Code] Variational autoencoders notebook Open In Colab
       
Mon 11 May Geometric deep learning slides ; video  
       
Wed 13 May [Code] Geometric deep learning notebook Open In Colab
       
Mon 18 May Adversarial training slides ; video  
       
Wed 20 May [Code] CycleGAN and adversarial attacks notebook Open In Colab
       
Mon 25 May Conclusions slides ; video  
       

End