Data Science for Document Analysis and Understanding

Scientific program

Week 1

Background Material (linear algebra and convex optimization)

Data Science (applications, kernels, classification, kernel PCA/CCA, dependency measures/distances, hypothesis testing, acceleration schemes.)

Practical Projects

Professional advising (CV, resume, PhD scholarship application.)


Week 2

Natural Language Processing (NLP) (Foundations of NLP: corpora, tokenization, stemming, term vector representations, POS tagging, parsing, language models, stopwords, text classification and clustering, dialogue systems. Deep learning in NLP: recurrent neural networks, LSTM, word vector representations, end-to-end dialogue systems.)

Practical Projects

Professional advising (CV, resume, PhD scholarship application.)

Course leader

Jing-Rebecca Li, Research Scientist, INRIA-Saclay

Target group

The target audience are students having completed advanced classwork in mathematics, statistics, or computer science. We accept Master's students as well as PhD students.

Course aim

The France Excellence 2018 Summer School “Data Science for Document Analysis and Understanding" will take place from July 16 to 27, 2018 at INRIA-Saclay. We aim to teach the fundamental concepts and important developments in data science and natural language processing.

Fee info

EUR 300: Cost: 300 euros

Included Scientific program.
Lunches Monday - Friday from July 16 - July 27.

Scholarships

Available.