Study programme 2020-2021Français
Advanced Machine Learning and Deep Learning
Programme component of Master's in Mathematics à la Faculty of Science

Students are asked to consult the ECTS course descriptions for each learning activity (AA) to know what special Covid-19 assessment methods are possibly planned for the end of Q3

CodeTypeHead of UE Department’s
contact details
Teacher(s)
US-M1-SCMATH-058-MOptional UESIEBERT XavierF151 - Mathématique et Recherche opérationnelle
  • SIEBERT Xavier
  • MAHMOUDI Sidi

Language
of instruction
Language
of assessment
HT(*) HTPE(*) HTPS(*) HR(*) HD(*) CreditsWeighting Term
  • Anglais
Anglais303000055.001st term

AA CodeTeaching Activity (AA) HT(*) HTPE(*) HTPS(*) HR(*) HD(*) Term Weighting
I-MARO-202Advanced Machine Learning2424000Q180.00%
I-ILIA-202Advanced Deep Learning66000Q120.00%
Programme component

Objectives of Programme's Learning Outcomes

  • Have integrated and elaborate mathematical knowledge.
    • Mobilise the Bachelor's course in mathematics to address complex issues and have profound mathematical expertise to complement the knowledge developed in the Bachelor's course.
    • Use prior knowledge to independently learn high-level mathematics.
  • Apply innovative methods to solve an unprecedented problem in mathematics or within its applications.
    • Mobilise knowledge, and research and analyse various information sources to propose innovative solutions targeted unprecedented issues.
    • Appropriately make use of computer tools, as required by developing a small programme.
  • Adapt to different contexts.
    • Have developed a high degree of independence to acquire additional knowledge and new skills to evolve in different contexts.
    • Critically reflect on the impact of mathematics and the implications of projects to which they contribute.
    • Demonstrate thoroughness, independence, creativity, intellectual honesty, and ethical values.

Learning Outcomes of UE

Get familiar with the contemporary methods in machine learning (active learning, reinforcement learning, depp networks) Study these methods within the frameworks of statistical learning theory      

 

Content of UE

active learning, reinforcement learning, deep networks, statistical learning theory

Prior Experience

basic knowledge in data mining / machine learning
python programming
mathematical bases

Type of Assessment for UE in Q1

  • Presentation and/or works
  • Written examination

Q1 UE Assessment Comments

personal work + written exam

Type of Assessment for UE in Q3

  • Presentation and/or works
  • Written examination

Q3 UE Assessment Comments

idem Q1

Type of Resit Assessment for UE in Q1 (BAB1)

  • N/A

Q1 UE Resit Assessment Comments (BAB1)

n/a

Type of Teaching Activity/Activities

AAType of Teaching Activity/Activities
I-MARO-202
  • Cours magistraux
  • Travaux pratiques
I-ILIA-202
  • Cours magistraux
  • Travaux pratiques
  • Projet sur ordinateur
  • Etudes de cas

Mode of delivery

AAMode of delivery
I-MARO-202
  • Mixed
I-ILIA-202
  • Mixed

Required Reading

AA
I-MARO-202
I-ILIA-202

Required Learning Resources/Tools

AARequired Learning Resources/Tools
I-MARO-202Not applicable
I-ILIA-202Not applicable

Recommended Reading

AA
I-MARO-202
I-ILIA-202

Recommended Learning Resources/Tools

AARecommended Learning Resources/Tools
I-MARO-202Not applicable
I-ILIA-202Not applicable

Other Recommended Reading

AAOther Recommended Reading
I-MARO-202Not applicable
I-ILIA-202Not applicable

Grade Deferrals of AAs from one year to the next

AAGrade Deferrals of AAs from one year to the next
I-MARO-202Unauthorized
I-ILIA-202Unauthorized
(*) HT : Hours of theory - HTPE : Hours of in-class exercices - HTPS : hours of practical work - HD : HMiscellaneous time - HR : Hours of remedial classes. - Per. (Period), Y=Year, Q1=1st term et Q2=2nd term
Date de génération : 09/07/2021
20, place du Parc, B7000 Mons - Belgique
Tél: +32 (0)65 373111
Courriel: info.mons@umons.ac.be