Pierre Monnin
Junior Fellow in AI at Université Côte d'Azur
Research within the Wimmics team
Teaching within EFELIA Côte d'Azur
I3S Laboratory
930 Route des Colles, BP 145
06903 Sophia Antipolis Cedex, France
Classes were taught in French unless otherwise stated
Focus on Natural Language Processing, tasks, (past to modern) models, limits, and applications in professional settings
Introduction to Artificial Intelligence, Machine Learning, Deep Learning, training process, Neural Networks, evaluation, Natural Language Processing, associated tasks, impacts on society and environment
Introduction to Artificial Intelligence, Machine Learning, Deep Learning, training process, Neural Networks, evaluation, Natural Language Processing, associated tasks, impacts on society and environment
Introduction to Artificial Intelligence, Machine Learning, Deep Learning, training process, Neural Networks, evaluation, associated tasks, impacts on society and environment
Introduction to Artificial Intelligence, Machine Learning, Deep Learning, training process, Neural Networks, evaluation, Generative AI / LLMs, associated tasks and challenges, with applications in manufacturing and services
Introduction to graph machine learning for knowledge graph refinement, some knowledge graph embedding models, link prediction, and evaluation
Document-oriented databases (MongoDB), search engines (Elasticsearch), key-value databases (Redis), column-oriented databases (HBase), graph databases (Neo4J)
Academic supervision of five M.Sc. Year 2 internships: monitoring interns' work in companies, report grading
Introduction to Artificial Intelligence, Machine Learning, Deep Learning, training process, Neural Networks, evaluation, Natural Language Processing, associated tasks, impacts on society and environment
Introduction to Artificial Intelligence, Machine Learning, Deep Learning, training process, Neural Networks, evaluation, Natural Language Processing, associated tasks, impacts on society and environment
Introduction to Artificial Intelligence, Machine Learning, Deep Learning, training process, Neural Networks, evaluation, Natural Language Processing, image generation, associated tasks, impacts on society and environment
Introduction to Artificial Intelligence, Machine Learning, Deep Learning, training process, Neural Networks, evaluation, associated tasks, impacts on society and environment
Introduction to graph machine learning for knowledge graph refinement, some knowledge graph embedding models, link prediction, and evaluation
XML language, DTD, XQuery, XSLT
Basics of Machine Learning, supervised and unsupervised learning, neural networks (MLP, CNN), training process, evaluation
Academic supervision of a M.Sc. Year 2 student for his research project (subject proposal, supervision, report and oral defense grading)
Academic supervision of two M.Sc. Year 2 internships: monitoring interns' work in companies, report grading
Artificial Intelligence, supervised and unsupervised learning (e.g., decision trees, neural networks, backpropagation algorithm, multilayer perceptron, K-means, Kohonen maps), Markov decision processes, knowledge graphs and the Semantic Web (RDF, ontologies, OWL reasoning, SPARQL), introduction to advanced AI techniques (e.g., CNN, GNN), applications & limits of AI, eXplainable AI, neuro-symbolic AI
Semantic Web (RDF, ontologies, OWL reasoning, SPARQL)
Introduction to algorithms (variables, assignments, conditions, loops, subalgorithms, etc.)
HTML, CSS, and an introduction to JavaScript
Proficient use of Word, Excel, and Internet Research
Basic concepts of the Java language and Object Oriented Programming
Advanced concepts of the Java language (collections, threads, User Interface, etc.)
Best, worst, and average case complexity, sorting algorithms, recursion, de-recursion, randomized algorithms, greedy algorithms, dynamic programming, backtracking, data structures (stacks, queues, heaps, graphs)
Introduction to programming in Python
First-order logic, Description Logics, Formal Concept Analysis, itemsets, association rules, Knowledge Graphs, Semantic Web (RDF, SPARQL) and applications
Turing machines, uncomputability, undecidability, complexity (e.g., big O notation)
Introduction to GNU/Linux and Git for development and project management
Description Logics, SPARQL
Search algorithms (e.g., A*, alpha-beta pruning), genetic algorithms, constraint satisfaction problems, Markov decision processes, supervised and unsupervised learning (e.g., decision trees, neural networks, backpropagation algorithm, multilayer perceptron, K-means, Kohonen maps)
Semantic Web (RDF, ontologies, OWL reasoning, SPARQL), Prolog
Document-oriented databases (MongoDB), search engines (Elasticsearch), key-value databases (Redis), column-oriented databases (HBase), graph databases (Neo4J)
Search algorithms (e.g., A*, alpha-beta pruning), genetic algorithms, constraint satisfaction problems, Markov decision processes, supervised and unsupervised learning (e.g., decision trees, neural networks, backpropagation algorithm, multilayer perceptron, K-means, Kohonen maps)
Semantic Web (RDF, ontologies, OWL reasoning, SPARQL), Prolog
Sorting algorithms, complexity, recursivity, back-tracking, Hoare logic
LR(0), SLR(1), LR(1) and LALR(1) parsers, Symbol Tables, Abstract Syntax Trees, assembly code generation