Parcours Communications engineering and data science (CODAS)

Voir la page complète

This course has for objectives to develop proficiencies in algorithms analysis, algorithm writing, and problem solving in general using algorithms.
This course uses Problem Based Learning methods for teaching, so students are expected to work in groups of 5-6 people during class sessions, and will do homework alone between sessions.
Students will solve four big problems during the semester, spanning about 4-6 sessions each. The problems will cover the following topics: advanced data structures (designing data structures to help solving a problem), greedy algorithms, dynamic programming, approximation algorithms, and more importantly the orthogonal notions of algorithm complexity and algorithm quality (in terms of solution produced).

Voir la page complète

This module about the English language includes oral and written communication tools. It teaches how to write professional documents: CV, articles, memorandum, e-mail, letter, master’s…

Moreover, it proposes a training specialised in scientific report writing using written communication techniques and tools and provides the skills to publish reviews or scientific reports (for example technicians). That course will enable people to do a work of quality that they can publish further in scientific magazines.

Voir la page complète

Voir la page complète

Voir la page complète

Voir la page complète

Voir la page complète

The aim of this course is to present the statistical approaches for analysing multivariate data. The information age has resulted in masses of multivariate data in many different field: finance, marketing, economy, biology, environmental sciences,…The theoretical and practical aspects of multivariate data analysis are given equal importance. This balance is achieved through practicals involving actual data analysis using the R software.

Content

1. Multiple linear regression. Least squares, Gaussian linear model, test of linear hypotheses, one-way analysis of variance.
2. Principal Components Analysis (PCA).
3. Classification, linear discriminant analysis, perceptron, Naive Bayes
4. Text mining, numeric representation of texts, connexion with graph clustering.

Voir la page complète

The aim of this course is to present the statistical approaches for analysing multivariate data. The information age has resulted in masses of multivariate data in many different field: finance, marketing, economy, biology, environmental sciences,…The theoretical and practical aspects of multivariate data analysis are given equal importance. This balance is achieved through practicals involving actual data analysis using the R software.

Content :

•     Multiple linear regression. Least squares, Gaussian linear model, test of linear hypotheses, one-way analysis of variance.
•     Principal Components Analysis (PCA).
•     Classification, linear discriminant analysis, perceptron, Naive Bayes
•     Text mining, numeric representation of texts, connexion with graph clustering.

Voir la page complète

Voir la page complète

The objective is a better understanding of the research world. This course overviews the principles of academic research conducted in research lab. First, it presents Grenoble’s academic landscape and the main research institutions. Moreover, it presents the principles of academic research. Then, it presents method guidelines to a) conduct successful research, b) read and write papers, give research talks.

Voir la page complète

Databases today  are essential to every business, corporation  and  many scientific investigations. They are behind  major  popular  systems as Google  or Amazon, they  store  important data of many  kind of companies and they are  even key components in research on physics, biology, health and several other fields. Database Management Systems (DBMS)  are powerful, but complex, systems  for creating  and managing  large amounts of data efficiently  and allowing it to persist over the time. In this course, we shall learn the foundations of DBMS and  most important  aspects  to design and to use  relational databases.

Program summary :
The theoretic part covers the following topics: DBMS functionalities, overview of the most common data models, the relational approach (algebra, SQL, normalization, etc.) ,  transactional support  and database design. We study database schema design using the entity-relation model and introduce an algorithm to translate such an abstraction to a normalized relational schema.  The pragmatic part of the course is intended to familiarize students with the use of the Standard Query Language, SQL. We also introduce JDBC, the Java API to access
relational databases.

Voir la page complète

Voir la page complète

Voir la page complète

Voir la page complète

Causality is at the core of our vision of the world and of the way we reason. It has long been recognized as an important concept and was already mentioned in the ancient Hindu scriptures: “Cause is the effect concealed, effect is the cause revealed”. Even Democritus famously proclaimed that he would rather discover a causal relation than be the king of presumably the wealthiest empire of his time. Nowadays, causality is seen as an ideal way to explain observed phenomena and to provide tools to reason on possible outcomes of interventions and what-if experiments, which are central to counterfactual reasoning, as ‘‘what if this patient had been given this particular treatment?’’

Voir la page complète

Machine Learning is one of the key areas of Artificial Intelligence and it concerns the study and the development of quantitative models that enables a computer to perform tasks without being explicitly programmed to do them. Learning in this context is hence to recognize complex forms and to make intelligent decisions. Given all existing entries, the difficulty of this task lies in the fact that all possible decisions is usually very complex to enumerate. To get around that, machine learning algorithms are designed in order to gain knowledge on the problem to be addressed based on a limited set of observed data extracted from this problem. To illustrate this principle, consider the supervised learning task, where the prediction function, which infers a predicted output for a given input, is learned over a finite set of labeled training examples, where each instance of this set is a pair constituted of a vector characterizing an observation in a given vector space, and an associated desired response for that instance (also called desired output). After the training step, the function returned by the algorithm is sought to give predictions on new examples, which have not been used in the learning process, with the lowest probability of error. The underlying assumption in this case is that the examples are, in general, representative of the prediction problem on which the function will be applied. We expect that the learning algorithm produces a function that will have a good generalization performance and not the one that is able to perfectly reproduce the outputs associated to the training examples. Guarantees of learnability of this process were studied in the theory of machine learning largely initiated by Vladimir Vapnik. These guarantees are dependent on the size of the training set and the complexity of the class of functions where the algorithm searches for the prediction function. Emerging technologies, particularly those related to the development of Internet, reshaped the domain of machine learning with new learning frameworks that have been studied to better tackle the related problems. One of these frameworks concerns the problem of learning with partially labeled data, or semi-supervised learning, which development is motivated by the effort that has to be made to construct labeled training sets for some problems, while large amount of unlabeled data can be gathered easily for these problems. The inherent assumption, in this case, is that unlabeled data contain relevant information about the task that has to be solved, and that it is a natural idea to try to extract this information so as to provide the learning algorithm more evidence. From these facts were born a number of works that intended to use a small amount of labeled data simultaneously with a large amount of unlabeled data to learn a prediction function.

The intent of this course is to propose a broad introduction to the field of Machine Learning, including discussions of each of the major frameworks, supervised, unsupervised, semi-supervised and reinforcement learning.

Voir la page complète

The course is split into two parts. During the first part, a wide range of machine learning algorithms will be discussed. The second part will focus on deep learning, and presentations more applied to the three data modalities and their combinations. The following is a non-exhaustive list of topics discussed:

• Computing dot products in high dimension & Page Rank
• Matrix completion/factorization (Stochastic Gradient Descent, SVD)
• Monte-carlo, MCMC methods: Metropolis-Hastings and Gibbs Sampling
• Unsupervised classification: Partitionning, Hierarchical, Kernel and Spectral clustering
• Alignment and matching algorithms (local/global, pairwise/multiple), dynamic programming, Hungarian algorithm,…
• Introduction to Deep Learning concepts, including CNN, RNN, Metric learning
• Attention models: Self-attention, Transformers
• Auditory data: Representation, sound source localisation and separation.
• Natural language data: Representation, Seq2Seq, Word2Vec, Machine Translation, Pre-training strategies, Benchmarks and evaluation
• Visual data: image and video representation, recap of traditional features, state-of-the-art neural architectures for feature extraction
• Object detection and recognition, action recognition.
• Multimodal learning: audio-visual data representation, multimedia retrieval.
• Generative Adversarial Networks: Image-image translation, conditional generation

Voir la page complète

Voir la page complète

Voir la page complète

Voir la page complète

Voir la page complète