README.md

DeepLearningUB.github.io

Deep Learning MSc Course 2020-2021

Deep learning is one of the fastest growing areas of machine learning and a hot topic in both academia and industry. This course will cover the basics of deep learning by using a hands-on approach.

Course Instructor

Jordi Vitrià, Departament de Matemàtiques i Informàtica de la UB.

Class Time and Location

• First Semester (September, 2020 - January, 2021)
• Face-to-face Lectures: Thursday 15:00h-16:00h
• Location: Aula T1, Facultat de Matemàtiques i Informàtica, Universitat de Barcelona.

Syllabus

• Introduction | Slides
• McKinsey DataLab (15/10/20, 2:00 to 4:00 p.m.)
• Basic Concepts: Machine Learning and Optimization | Slides
• SGD and Automatic Differentiation | Slides
• Tensorflow and Keras | Notebook
• Convolutional Neural Networks | Slides | Notebook1 | Notebook2
• Contrastive & Self-Supervised Learning | Slides | Notebook
• Deep Sequential Models | Slides | Notebook
• Deep Representations of Words | Slides | Notebook1 | Notebook2
• Attention and Context-based Embeddings | Slides
• Non Supervised Learning | Slides

Assignment

• 1st assignment: Designing and training a neural network from scratch: notebook. Due data: 30/10.
• 2ond assignment: Facial Point Detection with CNN: notebook. Due data: 30/11.
• 3rd assignment: Colors and Words: notebook. Due data: 15/01.