logo Insalogo Insa

IA Frameworks


Program (detailed contents) :

  • Introduction to the Spark Hadoop framework with PySpark.
  • Introduction to cloud computing with Google Cloud.
  • Introduction to container with docker
  • Introduction to natural language processing applying to text classification (text mining, vectorization, classification) and generation (recurrent neural network).
  • Recommendation system
  • Introduction to reinforcement learning.


Organization :

  • Lectures : 20H
  • Workshops, tutorials and self learning: 20h


Main difficulties for students :

  • Apprehend new technologies and use them to handle Artificial Intelligence challenge.


This course follows the Machine Learning and the High Dimensional & Deep Learning.

At the end of this module, the student will be able to run efficiently these algorithms on various technology.

It will also learn different algorithms on real dataset.


At the end of this module, the student will have understood and be able to explain (main concepts) :

  •  Scalability concepts (volume, variety, velocity) of big data analytics methods.
  • Properties of main big data frameworks (Python, Spark). Map Reduce.
  • Properties of container images.
  • Main algorithms of Natural language processing.
  • Reinforcement learning.


The student will be able to :

  • Clean, prepare, transform (munging) big data within Python or Spark frameworks.
  • Identify the right tool to analyse these big data (virtual machine ,container, gpus, etc..) on different use case.
  • Identify the right algorithm according to the data (recommendation system, NLP, rreinforcement learning, cnn
  • Execute, optimize, these methods and algorithms in the best adapted framework and validate their performances.
  • Learn by himself and develop a use case for a recent technology of his choice.

Needed prerequisite

Probability and statistics
Elements of statistical modelling [I4MMMS71]
Softwares and methods of statistical exploratory data analysis [I4MMSP81]

Form of assessment

The evaluation of outcome prior learning is made as a continuous training during the semester. According ot the teaching, the assessment will be different: as a written exam, an oral exam, a record, a written report, peers review...