Goto

Collaborating Authors

 gustavo stolovitzky


AI Competitions and Benchmarks, Practical issues: Proposals, grant money, sponsors, prizes, dissemination, publicity

arXiv.org Artificial Intelligence

Each organization of competitions and benchmarks involves a large number of practical problems, such as obtaining sufficient financial support or recruiting participants through appropriate incentives and community engagement. In addition to defining scientific tasks, preparing data and creating challenges, a very important practical administrative organization remains to be achieved. Indeed, cost assessment, corresponding requests for financial support and adequate publicity are key factors for successful organization of the competition. In addition, a good understanding of the incentives that lead participants to engage in a given challenge is fundamental for effective practical organization success. In this chapter, we will cover these topics and give some practical tips and examples for overcoming the "challenge" of organizing the challenges. How to incentivize participants to work on complex problems is a key feature of challenge organization. In this section, we review various types of motivations (Figure 1.1), from a participant perspective, and give practical tips to optimize those incentives.


AI Competitions and Benchmarks: The life cycle of challenges and benchmarks

arXiv.org Artificial Intelligence

Data Science research is undergoing a revolution fueled by the transformative power of technology, the Internet, and an ever-increasing computational capacity. The rate at which sophisticated algorithms can be developed is unprecedented, yet they remain outpaced by the massive amounts of data that are increasingly available to researchers. Here we argue for the need to creatively leverage the scientific research and algorithm development community as an axis of robust innovation. Engaging these communities in the scientific discovery enterprise by critical assessments, community experiments, and/or crowdsourcing will multiply oppor-DREAM Challenges e-mail: gustavo.stolo@gmail.com Coordinated community engagement in the analysis of highly complex and massive data has emerged as one approach to find robust methodologies that best address these challenges. When community engagement is done in the form of competitions -- also known as challenges -- the validation of the analytical methodology is inherently addressed, establishing performance benchmarks. Finally, challenges foster open innovation across multiple disciplines to create communities that collaborate directly or indirectly to address significant scientific gaps. Together, participants can solve important problems as varied as health research, climate change, and social equity. Ultimately, challenges can catalyze and accelerate the synthesis of complex data into knowledge or actionable information, and should be viewed a powerful tool to make lasting social and research contributions. The idea of leveraging a community of experts and non-experts to solve a scientific problem has been around for hundreds of years. One early example is the 1714 British Board of Longitude Prize, which was to be awarded to the person who could solve arguably the most important technological problem of the time: to determine a ship's longitude at sea [2]. After eluding many established scientists of the time, the prize was awarded to John Harrison for his invention of the marine chronometer.