Radboud Artificial Intelligence Event

15/12/2020 - 11:4515/12/2020 - 17:00

For over 30 years, Radboud University has been a global frontrunner on research about innovative intelligent learning systems. We develop new know-how and technologies that connect different fields of AI but also science and society in a responsible manner. 

Because our society faces complex challenges that require interdisciplinary collaboration, we reach out and encourage AI practitioners from industry and governmental organizations to join our Radboud AI Event. Since we all have a part to play, we invite you to meet us and join our masterclasses and network drinks at December 15th, 2020!​

 

Program Radboud AI Event 

11:45 Walk in with sandwiches 

12:15 Introduction AI prof. dr. Marcel van Gerven

13:00 Advances in deep learning dr. Jonas Teuwen On of the most active research directions in deep learning nowadays is in generative modelling where one  tries to model a probability distribution given samples drawn from that distribution. As these models intend to capture the underlying distribution, they are an important candidate for many unsupervised learning  problems.  

Therefore, over the past few years, many different generative models have been proposed. In this talk we  will focus on Normalizing Flows, which are a class of generative models which produce tractable  distributions where both sampling and density evaluation are computationally efficient and exact. We will also discuss their connection to invertible neural networks which have independently attracted much  interest due their favourable memory requirements and their connections to differential equations. 

13:45 Probabilistic Machine Learning dr. Luca Ambrogioni The masterclass will cover the basic principle behind Bayesian deep learning and variational inference. After an introduction into stochastic variational inference, variational autoencoders and the reparameterization  trick we will explain more advanced advanced topics such as Wasserstein variational inference and  normalizing flows.

14:30 Coffee break

14:45 Large-scale Federated Search prof. dr. Djoerd Hiemstra In federated search, independent search engines owned and operated by different stakeholders cooperate   to collectively provide a search service. In the masterclass: • several scenarios will be discussed with minimal cooperation between search engines • various use cases will be showed such as enterprise search • machine learning approaches will be discussed based on building language models from the results   obtained from search engines, as well as future work that used externally trained language models and   transfer learning as an effective approach to federated search.

15:30 Speech Technology dr. Henk van den Heuvel Automatic speech recognition is a powerful means to get to grips with your audio and video data.   Applications are manyfold nowadays. An overview will be presented of inspiring and surprising examples,   showing thestrength of the technology but also its weaknesses. Some of these weaknesses have been   tackled and will be shown in recent applications. 

16:15 Wrap-up prof. dr. Marcel van Gerven

16:45 Network drinks

Who should attend and why?

​AI practitioners such as software engineers, data-scientists, data analysts and researchers.

You will: 

• gain insight into the newest developments of AI

• gain the newest practical and scientific insights into Machine Learning

• expand your network 

• become part of the Radboud AI network  

 

Van der Valk Hotel Nijmegen-Lent
Oost NL
meer info en aanmelden