Learning Outcomes of UE

Keras (Python) framework for training deep neural nets
Deep reinforcment learning
SLAM (Simultaneous Localization and Mapping) for automatic cartography
Natural language processing

UE Content: description and pedagogical relevance

Three challenges to discover the tools of AI

Prior Experience

Practical knowledge of programming language (preferably python)

Type(s) and mode(s) of Q1 UE assessment

• Production (written work, report, essay, collection, product, etc.) - To be submitted online

Q1 UE Assessment Comments

If one or more challenge reports are missing, this activity will be graded ABS.
If the seminar report is missing, this activity will be graded ABS

Method of calculating the overall mark for the Q1 UE assessment

The overall score is 80% for challenges and 20% for seminars.
If one or more challenge reports are missing, this activity will be graded ABS.
If the seminar report is missing, this activity will be graded ABS.

Type(s) and mode(s) of Q1 UE resit assessment (BAB1)

• N/A - Néant

Q1 UE Resit Assessment Comments (BAB1)

n/a

Method of calculating the overall mark for the Q1 UE resit assessment

n/a

Type(s) and mode(s) of Q3 UE assessment

• Production (written work, report, essay, collection, product, etc.) - To be submitted online

Q3 UE Assessment Comments

If one or more challenge reports are missing, this activity will be graded ABS.
If the seminar report is missing, this activity will be graded ABS

Method of calculating the overall mark for the Q3 UE assessment

The overall score is 80% for challenges and 20% for seminars.