Code | Type | Head of UE | Department’s contact details | Teacher(s) |
---|---|---|---|---|
US-M2-INFOFS-006-M | Compulsory UE | GOSSELIN Bernard | F105 - Théorie des circuits et Traitement du signal |
Language of instruction | Language of assessment | HT(*) | HTPE(*) | HTPS(*) | HR(*) | HD(*) | Credits | Weighting | Term |
---|---|---|---|---|---|---|---|---|---|
Anglais | 0 | 0 | 0 | 0 | 0 | 4 | 4 |
AA Code | Teaching Activity (AA) | HT(*) | HTPE(*) | HTPS(*) | HR(*) | HD(*) | Term | |
---|---|---|---|---|---|---|---|---|
I-TCTS-005 |
Objectives of general skills
- Manage large-scale software development projects.
- Apply, mobilise, articulate and promote the knowledge and skills acquired in order to help lead and complete a project.
- Lead a project by mastering its complexity and taking into account the objectives, allocated resources and constraints that characterise it.
- Manage research, development and innovation.
- Understand unprecedented problems in computer science and its applications.
- Methodically research valid scientific information, lead a critical analysis, propose and argue potentially innovative solutions to targeted problems.
- Master communication techniques.
- Where possible, communicate in a foreign language.
- Develop and integrate a high degree of autonomy.
- Pursue further training and develop new skills independently.
- Apply scientific methodology.
- Critically reflect on the impact of IT in general, and on the contribution to projects.
- Skill 2: Have acquired professional skills in relation to the objective defining the degree.
- Specialise in at least one sub-domain of computer science.
- Integrate into a professional environment and collaborate with stakeholders on a project.
UE's Learning outcomes
develop an applied pattern recognition system, together with a critical analysis of the problem;
apply data processing techniques (feature extraction, feature selection);
apply classification techniques and train classifiers (Gaussian modelling, Clustering, Artificial Neural Networks, Support Vector Machines, Dynamic Time Warping, Hidden Markov Models, Combining Classifiers);
estimate performances of classifiers.
UE Content
fundamentals: SPR scheme, feature extraction, classifiers, combining classifiers; neural networks: feed-forward neural networks, training MLP, other ANN models; support vector machines; dynamic systems: dynamic time warping, hidden Markov models; Speech Processing and Recognition
Prior experience
fundamentals of signal processing; probability and statistics
Term 1 for Integrated Assessment - type
- N/A
Term 1 for Integrated Assessment - comments
Not applicable
Term 2 for Integrated Assessment - type
- Oral Examination
Term 2 for Integrated Assessment - comments
Not applicable
Term 3 for Integrated Assessment - type
- Oral examination
Term 3 for Integrated Assessment - comments
Not applicable
Resit Assessment for IT - Term 1 (B1BA1) - type
- N/A
Resit Assessment for IT - Term 1 (B1BA1) - Comments
Not applicable
Type of Teaching Activity/Activities
AA | |
---|---|
I-TCTS-005 |
Mode of delivery
AA | |
---|---|
I-TCTS-005 |
Required Reading
AA | |
---|---|
I-TCTS-005 |
Required Learning Resources/Tools
AA | |
---|---|
I-TCTS-005 |
Recommended Reading
AA | |
---|---|
I-TCTS-005 |
Recommended Learning Resources/Tools
AA | |
---|---|
I-TCTS-005 |
Other Recommended Reading
AA | |
---|---|
I-TCTS-005 |