4th Seminar School on

Introduction to Deep Learning

Barcelona

UPC ETSETB TelecomBCN (June 21 - July 1, 2021)

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
Ramon Morros


Javier Ruiz
Elisa Sayrol
Veronica Vilaplana


Teaching Assistants

Gerard Gallego
(Lab)
Albert Mosella
(Lab)
Biel Tura
(Web)
Lectures

Lectures:

Course will be divided in different lectures covering the following topics:

  • 21/06 09:30-10:00 D1L1 (ES) Welcome
  • 21/06 10:00-10:30 D1L2 (ES) Machine Learning [PDF]
  • 21/06 10:30-11:00 D1L3 (ES) Perceptron and Multi-Layer Perceptron [PDF]
  • 22/06 09:30-10:30 D2L1 (RM) Backpropagation [PDF]
  • 22/06 10:30-11:30 D2L2 (JR) Loss functions [PDF]
  • 23/06 09:30-10:30 D3L1 (VV) Optimization [PDF]
  • 28/06 09:30-10:30 D4L1 (VV) Convolutional Neural Networks - CNNs [PDF]
  • 28/06 10:30-11:30 D4L2 (RM) Architectures [PDF]
  • 29/06 09:30-10:30 D5L1 (JR) Methodology [PDF]
  • 29/06 10:30-11:30 D5L2 (RM) Transfer Learning [PDF]
  • 30/06 09:30-10:00 D6L1 (XG) Interpretability [PDF]
  • 30/06 10:00-10:30 D6L2 (XG) Recurrent Neural Networks - RNNs [PDF]
  • 30/06 10:30-11:00 D6L3 (XG) Attention mechanism [PDF]
  • 30/06 11:00-11:30 D6L4 (XG) The Transformer architecture [PDF]

Lab Sessions:

  • 21/06 11:30-12:30 D1 Lab: Introduction to Tensors
  • 22/06 11:30-12:30 D2 Lab: Backpropagation
  • 23/06 10:30-11:30 D3 Lab: Multi-layer Perceptron
  • 28/06 11:30-12:30 D3 Lab: Optimization
  • 29/06 11:30-12:30 D4 Lab: Convolutional Neural Networks - CNNs
  • 29/06 11:30-12:30 D5 Lab: Overfitting
  • 30/06 11:30-12:30 D6 Lab: Transfer Learning
  • 01/07 11:30-12:30 D7 Lab: Interpretability

Exam:

  • 01/07 09:30-11:30 D7: Final online examination of the course
Practical

Practical details

  • Study Programs: Bachelor degrees at at ETSETB TelecomBCN and [Centre de Formació Interdisciplinària Superior (CFIS) (http://cfis.upc.edu/ca) from the Universitat Politecnica de Catalunya.
  • Course code and official guide: 230325 - IDL
  • ECTS credits: 2 ECTS
  • Teaching language: English
  • Semester: Spring 2021
  • Class Schedule: 21, 22, 23, 28, 29, 30 June & 1 July 2021 (9:30am-12:30pm Lectures & Lab)
  • Capacity: 40 students
  • Location: Campus Nord UPC
Registration

Registration

Registration procedure depends on the student profile:

  • Bachelor students at ETSETB who can register the 2 ECTS: Follow the regular schedule from your academic office. There is an extraordinary registration period in mid January.
  • Master students at ETSETB: This Seminar is a light version of the full MSc course of Deep learning for Artificial Intelligence, taught during the Autumn semester. So we encourage you to sign up for this other one.
  • 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. Industry: Those industry members interested in the topic are encouraged to apply for the UPC School postgradute course on Artificial Intelligence with Deep Learning.
Sponsors

Google Cloud



GitHub Education

Organizers

ETSETB
ETSETB Telecom BCN

UPC
Universitat Politècnica de Catalunya

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