Objectives of Programme's Learning Outcomes

• Mobilise a structured set of scientific knowledge and skills and specialised techniques in order to carry out computer and management engineering missions, using their expertise and adaptability.
• Master and appropriately mobilise knowledge, models, methods and techniques specific to computer management engineering.
• Analyse and model an innovative IT solution or a business strategy by critically selecting theories and methodological approaches (modelling, optimisation, algorithms, calculations), and taking into account multidisciplinary aspects.
• Identify and discuss possible applications of new and emerging technologies in the field of information technology and sciences and quantifying and qualifying business management.
• Assess the validity of models and results in view of the state of science and characteristics of the problem.
• Communicate and exchange information in a structured way - orally, graphically and in writing, in French and in one or more other languages - scientifically, culturally, technically and interpersonally, by adapting to the intended purpose and the relevant public.
• Argue to and persuade customers, teachers and boards, both orally and in writing.
• Adopt a professional and responsible approach, showing an open and critical mind in an independent professional development process.
• Exploit the different means available in order to inform and train independently.

Learning Outcomes of UE

At the end of this UE, the student should have acquired theoretical knowledge and practical skills related to two of the major paradigms of AI: "deep learning" and probabilistic models. He/she should :
- know the major applications of artificial intelligence to natural language,
- know some of the most recent machine learning methods,
- be able to implement complex artificial neural networks
- know how to use generic software libraries for deep learning
- understand the importance and interest of the probabilistic perspective in AI.
- know the basic theory of probabilistic graphical models and Bayesian networks.
- know the hidden Markov models, particle filters, mixtures of Gaussians, and the latent Dirichlet allocation.
- be able to put into practice statistical inference approaches.
- know how to use software libraries dedicated to probabilistic programming (PyMC3, Pyro, etc.).
 

Content of UE

The UE is composed of two learning activities that expose two complementary methodologies to AI:
- artificial intelligence through deep learning applied to the modeling of time sequences, and in particular to natural language processing (chatbots, machine translation, information extraction, etc.)
- artificial intelligence relying on probability theory, based on probabilistic graphical models, Bayesian networks, and their implementation through probabilistic programming.

These learning activities will include practicals to acquire the theory.

More details about the content are provided in the ECTS sheets of each learning activity.

Prior Experience

Not applicable

Type of Assessment for UE in Q2

• Presentation and/or works
• Oral Examination
• Practical test
• Graded tests

Q2 UE Assessment Comments

Not applicable

Type of Assessment for UE in Q3

• Presentation and/or works
• Oral examination
• Practical Test
• Graded tests

Q3 UE Assessment Comments

Not applicable