Edition 2022 - 2023

We have entered the Big Data Era. The explosion of available data in a wide range of application domains give rise to new challenges and opportunities in a plethora of disciplines – ranging from science and engineering to business and society in general. A major challenge arises in the question of how to take advantage of this unprecedented scale of data, in order to acquire further insights and knowledge for improving the quality of the offered services. This is where Machine and Deep Learning comes in capitalizing on techniques and methodologies from data exploration (statistical profiling, visualization), aiming to identify patterns, correlations, groupings, modeling and predicting. In this domain, Deep learning is becoming a very important element for solving large scale prediction problems in recent years. 
 
 

Course Logistics

1. The course will take place on Monday and Wednesday afternoons beginning on 19/09/2022 as follows (Please check the synapses platform to see which group (Gr) you were assigned to, to determine your lab time and location):

  • Monday (14:00 - 16:00) magistral teaching in: Amphi Cauchy.
  • Monday (16:15 - 18:15) lab sessions in the small classes: Amphi Painlevé (Gr1), Amphi Poisson (Gr2), Amphi Sauvy (Gr3).
  • Wednesday (14:00 - 16:00)  lab sessions in the small classes: PC11 (Gr4), PC22 (Gr5), PC12 (Gr6).

 

2. Interaction/Q&As: 

We have set up a dedicated slack workspace for this course, which we will use to communicate with you. Please register to the following workspace with your full name and use it as much as possible.

https://join.slack.com/t/slack-ymb9142/shared_invite/zt-1fi2zfe6r-RmTe4OVpq6xJKSpcn9DNJg

 

3. The course will be assessed via:

  • (20% of the course mark) an individual take-home assessment handed out on Monday 3rd October with deadline on Monday 17th October 2pm.
  • (80% of the course mark) a group data challenge handed out on Monday 7th November with a written report deadline on Wednesday 7th December 5pm and oral assessments in the week of the 12th December. We will communicate further details about the formation of groups for the challenge at the start of November on the course slack channel.

 

4. You will have to complete the course work on your own laptops (preferably with a Unix environment like Linux or Mac OS X for compatibility reasons). As for software, we will be using  Python among others (to be installed locally on the laptops). Students are invited to install the current Anaconda distribution BEFORE the 1st lab session (https://www.anaconda.com/products/individual). Please also make sure that you have installed the PyTorch, numpy and scikit-learn python packages. 

 

 

Detailed syllabus of the course

(minor changes may apply during the course progression.)

 

 

General Introduction to Machine Learning

- Machine Learning paradigms
- The Machine Learning Pipeline

 

Supervised Learning

- Generative and non generative methods
- Naive Bayes, KNN and regressions
- Tree based methods

 

Unsupervised Learning

- Dimensionality reduction
- Clustering 

 

Advanced Machine Learning Concepts

- Regularization
- Model selection
- Feature selection
- Ensemble Methods

 

Kernels

- Introduction to kernels
- Support Vector Machines

 

Neural Networks

- Introduction to Neural Networks
- Perceptrons and back-propagation

 

Deep Learning I

- Convolutional Neural Networks
- Recurrent Neural Networks
- Applications

 

Deep Learning II

- Modern Natural Language Processing
- Unsupervised Deep Learning
- Embeddings, Auto-Encoders, Generative Adversarial Networks

 

Machine & Deep Learning for Graphs

- Graph Similarity 
- Graph Kernels 
- Node Embeddings

 




Edition 2020-21

We have entered the Big Data Era. The explosion and profusion of available data in a wide range of application domains rise up new challenges and opportunities in a plethora of disciplines – ranging from science and engineering to business and society in general. A major challenge is how to take advantage of the unprecedented scale of data, in order to acquire further insights and knowledge for improving the quality of the offered services, and this is where Machine and Deep Learning comes in capitalizing on techniques and methodologies from data exploration (statistical profiling, visualization) aiming at identifying patterns, correlations, groupings, modeling and doing predictions. In the last years Deep learning is becoming a very important element for solving large scale prediction problems. 

The Introduction to Machine and Deep Learning class will cover the following aspects:

  • The Machine Learning Pipeline
  • Unsupervised Learning
  • Data Preprocessing and Exploration
  • Feature Selection/Engineering & Dimensionality reduction
  • Supervised Learning 
  • Deep and Reinforcement Learning

 

Logistics

1. The course will take place on Mondays afternoon from 21/09/2020 for 9 weeks and will be divided into nine 4-hour sessions Due to the COVID situation we will conduct the course/labs with VIDEO online synchronous classes/labs

- magistral teaching (14:00 - 16:00) FOLLOW THIS ZOOM LINK FOR ALL CLASSES

-  online lab sessions (16:15 - 18:15) FOLLOW THIS ZOOM LINK FOR ALL LABS

 

Interaction/Q&As: 
As there is currently lack of physical co presence a slack channel was set up for individual questions to course/lab teachers: https://inf554workspace.slack.com. Please us it as much as possible. 
We will also set up some online video time slots to handle your questions in real time. 
 
We will also try to provide recorded versions of the class and the labs if the storage requirements can be met. 

IPPMaster and other students - access: 

you may get access to the course and material by registering to this form: 

we will then send you your guest access code. 

2. The students will have to complete the course work on their own laptops (preferably with a Unix environment like Linux or Mac OS X for compatibility reasons). As for software, we will be using  Python among others (to be installed locally on the laptops). Students are invited to install the Anaconda distribution version 3.7 BEFORE the 1st lab session.