6. Conclusion
Unsupervised statistical learning is a relatively recent discipline, which is still the subject of fundamental research and regularly gives rise to major innovations. Although this type of learning is more difficult to grasp and implement than supervised learning, and the techniques used are still evolving, it is already leading to spectacular successes, particularly in natural language processing and multimedia content generation.
SCROLL TO TOP
You do not have access to this resource.
Exclusive to subscribers. 97% yet to be discovered!
Already subscribed?
Log in!
Ongoing reading
Conclusion
Bibliography
-
(1) - KARRAS (T.), LAINE (S.), AILA (T.) - A Style-Based Generator Architecture for Generative Adversarial Networks - (2018).
-
(2) - KLEINBERG (J.) - An Impossibility Theorem for Clustering, - in NIPS (2002).
-
(3) - ESTER (M.), KRIEGEL (H.P.), SANDER (J.),...
Also in our database
-
BESSE (P.), BACCINI (A.) - Analyse des données ou statistiques exploratoire multidimensionnelle -
Software tools
For computations that do not involve deep learning and that deal with data volumes that do not require the use of distributed computing, the two reference software tools are scikit-learn and R
The Spark Mlib library adapts the main machine learning algorithms (excluding deep learning) to a distributed environment, enabling the processing of very large volumes of data.
Deep learning tools include pytorch and tensorflow/...
Events
Annual conferences :
International Conference on Learning Representations (https://iclr.cc/)
Conference on Neural Information Processing Systems (https://nips.cc/)
Conference on Computer Vision and Pattern Recognition
International Conference on Machine Learning (
You do not have access to this resource.
Exclusive to subscribers. 97% yet to be discovered!
Already subscribed?
Log in!