3rd Master Course on

Deep Learning for Artificial Intelligence

Universitat Politecnica de Catalunya

ETSETB TelecomBCN (Autumn 2019)

Previous editions: [2017] [2018] [All DL courses]

Deep learning technologies are at the core of the current revolution in artificial intelligence for multimedia data analysis. The convergence of large-scale annotated datasets and affordable GPU hardware has allowed the training of neural networks for data analysis tasks which were previously addressed with hand-crafted features. Architectures such as convolutional neural networks, recurrent neural networks or Q-nets for reinforcement learning have shaped a brand new scenario in signal processing. This course will cover the basic principles of deep learning from both an algorithmic and computational perspectives.

Instructors

Instructors

Xavier Giró
Marta R. Costa-jussà
Noé Casas
Veronica Vilaplana


Ramon Morros
Javier Ruiz
Albert Pumarola
Jordi Torres



Lab developers

Santiago Pascual
Daniel Fojo
Albert Pumarola

Guest Instructor

Yannis Kalantidis
Lectures

Lectures - Mondays 2-4pm - Room: A3-205

Course will be divided in modules of 50 minutes (aproximately) covering the following topics. Slides & videos from previous edition are available here.

  • 16/09 14:00 D01L1 (XG) Welcome
  • 16/09 15:00 D01L2 (XG) Machine Learning Basics [Slides]
  • 30/09 14:00 D02L1 (XG) The Perceptron [Slides] [Video 2018]
  • 30/09 14:30 D02L2 (XG) Backpropagation [Slides] [GIF] [Video 2017]
  • 30/09 15:30 D02L3 (XG) Softmax Regression [Slides]
  • 30/09 15:45 D02L4 (XG) Multi-Layer Perceptron [Slides] [Video 2017]
  • 07/10 14:00 D03L1 (VV) Convolutional Neural Networks [Slides from AA2 2019]
  • 07/10 15:00 D03L2 (VV) Deconvolving Neural Networks
  • 14/10 14:00 D04L1 (JR) Loss functions [Slides]
  • 14/10 15:00 D04L2 (VV) Optimization I
  • 21/10 14:00 D05L1 (VV) Optimization II
  • 21/10 14:30 D05L2 (JR) Methodology [Slides]
  • 28/10 14:00 D06L1 (MC) Recurrent Neural Networks [Slides] [Video 2017]
  • 28/10 15:00 D06L2 (MC) Attention-based models [Slides] [Video 2018]
  • 04/11 14:00 D07E1 (XG) Midterm exam
  • 04/11 15:00 D07L1 (XG) Interpretability [Slides] [Video 2018]
  • 11/11 14:00 D08L1 (XG) Neural Architectures from ImageNet [Slides]
  • 11/11 15:30 D08L1 (XG) Neural Architecture Search [Slides]
  • 18/11 14:00 D09L1 (RM) Transfer learning & Domain Adaptation [Slides] [Video 2018]
  • 18/11 15:00 D09L2 (RM) Incremental learning [Slides] [Video 2018]
  • 21/11 12:00 GUEST (YK) Learning efficient representation for image and video understanding [Slides]
  • 25/11 14:00 D10P1 (NC) Project
  • 25/11 15:00 D10L1 (XG) Self-supervised Learning [Slides] [Video MCV]
  • 02/12 14:00 D11P1 (NC) Project
  • 02/12 15:00 D12L1 (AP) Generative Adversarial Networks(GANs) [Slides] [Video 2018]
  • 09/12 14:00 D13P1 (NC) Project
  • 09/12 14:30 D13L1 (JT) Visit to the Barcelona Supercomputing Center (BSC)
  • 16/12 14:00 D14P1 (NC) Project presentations
  • 21/01 Final exam
Labs

Labs (15%) - Room: D5-004

The course will contain guided hands on lab that will lead the students in their first steps in deep learning frameworks. Students must bring their own laptops to follow these labs.

  • Lab01 (SP) A World of Tensors and Differentiable Computing [Notebook]
  • Lab02 (SP) Automatic Differentiation with PyTorch [Notebook]
  • Lab03 (SP) Linear regression [Notebook]
  • Lab04 (SP) Multi-Layer Perceptrons [Notebook]
  • Lab05 (SP) Convolutional Neural Networks [Notebook]
  • Lab06 (SP) Overfitting & Underfitting [Notebook]
  • Lab07 (DF) CNN Interpretability [Notebook]
  • Lab08 (SP) Recurrent Neural Networks & Attention [Notebook]
  • Lab09 (DF) Transfer Learning [Notebook]
  • Lab10 (AP) Generative Adversarial Networks [Notebook]
Practical

Practical details

  • Course on UPC Atenea
  • Study Programs: Master MET & Master MATT at ETSETB TelecomBCN from the Universitat Politecnica de Catalunya.
  • Course code and official guide: 230706 - DLAI
  • ECTS credits: 5 ECTS
  • Teaching language: English
  • Class Schedule: Mondays 2-5pm (2-4pm Lectures, 12-1pm, 4-5pm & 5-6pm Labs)
  • Capacity: 60 MSc students
  • Lectures: Campus Nord UPC, Module A3, Room 205
  • Labs: Campus Nord UPC, Module D5, Room 004
Registration

Registration

Registration procedure depends on the student profile:

  • Master students at ETSETB: Follow the regular schedule from your academic office.

  • Bachelor (grau) students at ETSETB and CFIS students: Do not register to this course but to “Introduction to Deep Learning”, a lighter version of this course offered as a intensive Winter School between 22-28 January 2020. Check with your academic office.

  • MSc Students at UPC but not in ETSETB: Contact the your academic office and request being allowed to take this course. If accepted, contact ETSETB academic office and request more details.

  • Other students currently enroled in another academic program outside UPC: You can request attending to the seminar by sending your CV and motivation letter to the ETSETB academic office, clearly showing your previous knowledge in deep learning and their software frameworks. If accepted, you will need to cover the full cost of the course (around 720 euros, which correspond to 5 ECTS). You must already be legally eligible to attend to this course, we will not release any acceptance later for visas.

  • Other profiles (eg. industry members): This course is not addressed to this audience. If you are interested in this topic, we suggest you consider the postgraduate program in Artificial Intelligence with Deep Learning from UPC School. This postgraduate extends the dep learning contents offered at UPC TelecomBCN. Next edition starts in November 2019.

Organizers

ETSETB
ETSETB Telecom BCN

UPC
Universitat Politècnica de Catalunya

Design by Tim O’Brien t413.com — SinglePaged theme — this site is open source