A major seaside resort town on the northern Bulgarian Black Sea Coast in the municipality of Varna.
- Paper Deadline:
May 15th May 22nd (extended)
- Author Notifications: July 10th, 2019 - Camera-ready: August 1st, 2019
Prof. Vladimir Vapnik (AI Research Facebook)
Prof. Alexander Balinsky (Cardiff School of Mathematics)
Professor Vladimir Vapnik
AI Research Facebook, USA; Royal Holloway, University of London, UK
Talk's title to be confirmed
Prof. Vapnik is one of the main developers of the Vapnik–Chervonenkis theory of statistical learning, and the co-inventor of the support-vector machine method, and support-vector clustering algorithm.
Professor Alexander Balinsky
Cardiff School of Mathematics, UK
Mathematics of Deep Learning
Deep Learning is another name for a set of algorithms that use a neural network as an architecture. In the past few years, Deep Learning has generated much excitement due to many breakthrough results in speech recognition, computer vision and text processing. This recent success has been due to new mathematical techniques, the availability of inexpensive, parallel hardware (GPUs, computer clusters) and massive amounts of data. This powerful way of processing data can be used to address an ever-growing number of problems, and its impact on science and society is increasing exponentially. In this talk we present mathematical foundations of Deep Learning, relations with physics , features extraction and interpretability. We also explain mathematics behind adversarial attacks and how to protect against them. Several new mathematical problems will be presented.
Prof. Balinsky was founding member of Cardiff Communication Research Centre. He had several Hewlett-Packard joint research projects. He also did consultancy work for Reuters, London on mathematical models for Internet Security. His Impact Case Study "Meeting the Challenges of Data Security: Detecting Unusual Behaviour and Mining Unstructured Data" was featured in the leading article 'The impact of impact' in Times Higher.
The main purpose of conformal prediction is to complement predictions delivered by various algorithms of Machine Learning with provably valid measures of their accuracy and reliability under the assumption that the observations are independent and identically distributed. It was originally developed in the late 1990s and early 2000s but has become more popular and further developed in important directions in recent years.
Conformal prediction is a universal tool in several senses; in particular, it can be used in combination with any known machine-learning algorithm, such as SVM, Neural Networks, Ridge Regression, etc. It has been applied to a variety of problems from diagnostics of depression to drug discovery to the behaviour of bots.
A sister method of Venn prediction was developed at the same time as conformal prediction and is used for probabilistic prediction in the context of classification. Among recent developments are adaptations of conformal and Venn predictors to probabilistic prediction in the context of regression.
The COPA series of workshops is a home for work in both conformal and Venn prediction, as reflected in its full name “Conformal and Probabilistic Prediction with Applications”. The aim of this symposium is to serve as a forum for the presentation of new and ongoing work and the exchange of ideas between researchers on any aspect of Conformal and Probabilistic Prediction and their applications to interesting problems in any field.
Topics of the symposium include, but are not limited to:
Authors are invited to submit original, English-language research contributions or experience reports. Papers should be no longer than 20 pages formatted according to the well-known JMLR (Journal of Machine Learning Research) style. The LaTeX package for the style is available here. All aspects of the submission and notification process will be handled online via the EasyChair Conference System at:
Researchers interested in Conformal Prediction may be interested in joining our online discussion group. Future announcements and related materials will be published regularly.