IJCNN 2019 Accepted Competitions


Number Title Organizers Description
C01 L2RPN: Learning to run a power network. 

Isabelle Guyon, Antoine Marot, Balthazar Donon, Benjamin Donnot

The objective of this challenge is to test the potential of Reinforcement Learning (RL) to solve a real world problem of great practical importance: controlling electricity trans- portation in power grids while keeping people and equipment safe. This challenge is the ”gamification” of a serious problem. We work in collaboration with the French long dis- tance high voltage electricity transmission company Rseau de Transport dlectricit (RTE, France). Contact: [email protected]

C02 AIML Contest 2019   Juyang Weng, Juan L. Castro-Garcia, Xiang Wu.  

The Artificial Intelligence Machine Learning (AIML) Contest aims to address major learning mechanisms for general purposes. It provides an opportunity for contestants to learn about brain-inspired models and algorithms. It is the first contest series that must use a task-independent and modality-independent learning engine. Contact: [email protected]

C03

AutoML Rematch

Wei-Wei Tu, Yao Quanming, Wang Mengshuo,  Hugo Jair Escalante, Isabelle Guyon. 

The goal is to develop Automatic Machine Learning methods in a lifelong setting, and where the data presents the concept drift phenomenon. This challenge is a follow up of a series of AutoML challenges collocated with PAKDD2018,  NIPS2018, and PAKDD2019. Contact: [email protected]

C04

Challenge UP: Multimodal Fall Detection

Hiram Ponce, Lourdes Martínez-Villaseñor, León Palafox, Karina Pérez 

Falls are frequent especially among old people and it is a major health problem according to World Health Organization. Fall detectors can alleviate this problem and can reduce the time in which a person who suffered a fall receives assistance. Recently, there has been an increase in fall detection system development based mainly in sensor and/or context approaches; however, public datasets are difficult to access. In that sense, we provide a public multimodal dataset for fall detection in the benefit of researchers in the fields of wearable computing, ambient intelligence, and vision. In the best of our knowledge, no fall detection competition has been reported, and especially using a multimodal dataset. Contact: [email protected]