Objectif du cours
The ALTEGRAD course ( 28 hours) aims at providing an overview of state-of-the-art ML and AI methods for text and graph data with a significant focus on applications. Each session will comprise two hours of lecture followed by two hours of programming sessions.
Grading for the course will be based on a final data challenge plus lab based evaluation.
TO ENROL – IMPORTANT !
All interested students should fill the following form to enrol: link to form
The ALTEGRAD challenge Fall 2017 topic is:
« Can you predict whether two short texts have the same meaning? »
You can find more information for the challenge here
Course web page: here
Course Syllabus 2017 :
- Graph-of-words advanced topics (1/2)
-Introduction to text preprocessing and NLP
-graph of words and information retrieval - Graph-of-words advanced topics (2/2)
-Keyword extraction, Summarization (abstrative, extractive)
-Graph based document categorization
-Event detection in text streams (twitter) - Word & document embeddings
-Introduction to NN architectires for NLP
-Latent Semantic Indexing
-Word embeddings: word2vec, glove models, word mover’s distance, doc2ve
Course Syllabus 2017 :
- Deep learning for NLP-Backpropagation for MLP architectures
-Deep Learning architectures for text classification (CNNs, RNNs, LSTMs) - Influential spreader detection, influence maximization
-single spreaders: epidemic models (SIR/SIS), baselines for spreaders selection
-multiple spreaders: LT/IC model, Greedy Algorithm - Graph kernels, community detection
-Graph Generators, Similarity, Kernels, Clustering/applications) - Deep Learning for Graphs (DeepWalk, Node Embeddings
– DeepWalk, LINE, GraRep, node2vec, Graph Classification with Patchy-San, Spectral Networks
Les intervenants
Michalis Vazirgiannis
(Polytechnique)