How to make AI more fair and unbiased | AI FOR GOOD DISCOVERY

Channel:
Subscribers:
19,500
Published on ● Video Link: https://www.youtube.com/watch?v=5eQgIIwG4IY



Duration: 0:00
549 views
0


AI-based decision-making has already penetrated into almost all spheres of human life, from content recommendation and healthcare to predictive policing and autonomous driving, deeply affecting everyone, anywhere, anytime. The discriminative impact of AI-based decision-making on certain population groups has been already observed in a variety of cases leading to an ever-increasing public concern about the impact of AI in our lives. The domain of fairness-aware machine learning focuses on methods and algorithms for understanding, mitigating, and accounting for bias in AI/ML models. Most of the work in this field focuses on limiting learning settings, typically binary classification with a binary protected attribute. The reality is, however, more complex. For example, discrimination can occur based on more than one protected attribute, the class distribution might be imbalanced, the population characteristics might change, and more than one learning task might need to be solved at the same time. \n\nIn the first part of the talk, Prof Eirini Ntoutsi talks about fairness in the basic binary class mono-discrimination setting. The second part covers recent work towards more realistic challenges like multi-task discrimination, discrimination under class imbalance and distribution shifts. \n\n Speakers:\nEirini Ntoutsi\nProfessor for Open Source Intelligence\nBundeswehr University  Munich\n\n Moderators:\nWojciech Samek\nHead of AI Department\nFraunhofer Heinrich Hertz Institute (HHI)\n\nJoin the Neural Network! \nhttps://aiforgood.itu.int/neural-network/\nThe AI for Good networking community platform powered by AI. \nDesigned to help users build connections with innovators and experts, link innovative ideas with social impact opportunities, and bring the community together to advance the SDGs using AI.\n\n Watch the latest #AIforGood videos!\n\n\nExplore more #AIforGood content:\n AI for Good Top Hits\n   • Top Hits  \n\n AI for Good Webinars\n   • AI for Good Webinars  \n\n AI for Good Keynotes\n   • AI for Good Keynotes  \n\n Stay updated and join our weekly AI for Good newsletter:\nhttp://eepurl.com/gI2kJ5\n\n Discover what's next on our programme!\nhttps://aiforgood.itu.int/programme/\n\nCheck out the latest AI for Good news:\nhttps://aiforgood.itu.int/newsroom/\n\nExplore the AI for Good blog:\nhttps://aiforgood.itu.int/ai-for-good-blog/\n\n Connect on our social media:\nWebsite: https://aiforgood.itu.int/\nTwitter: https://twitter.com/AIforGood\nLinkedIn Page: https://www.linkedin.com/company/26511907 \nLinkedIn Group: https://www.linkedin.com/groups/8567748 \nInstagram: https://www.instagram.com/aiforgood \nFacebook: https://www.facebook.com/AIforGood\n\nWhat is AI for Good?\nWe have less than 10 years to solve the UN SDGs and AI holds great promise to advance many of the sustainable development goals and targets.\nMore than a Summit, more than a movement, AI for Good is presented as a year round digital platform where AI innovators and problem owners learn, build and connect to help identify practical AI solutions to advance the United Nations Sustainable Development Goals.\nAI for Good is organized by ITU in partnership with 40 UN Sister Agencies and co-convened with Switzerland.\n\nDisclaimer:\nThe views and opinions expressed are those of the panelists and do not reflect the official policy of the ITU.




Other Videos By AI for Good


2022-12-12Can AI predict the next pandemic? The role of AI and genomics in combating infectious diseases
2022-12-11A fundamental problem of digital hardware: Will true trustworthiness require quantum computing?
2022-12-112022 ITU GeoAI Location Mention Recognition Challenge Finale
2022-12-08FG-AI4EE Workshop on Advancing Environmental Efficiency of Emerging Technologies
2022-12-08An “AI” Pathway Towards Sustainable Manufacturing | Discovery
2022-12-07Paving the way towards 100% network autonomy | AI for Good Webinar
2022-12-06Portrait XO – multi-model AI composing | Artistic Intelligence Visionary Initiative
2022-12-05Collective robotics: Multi-robot coordination in complex environments | AI for Good
2022-12-04AI for Good Innovation Factory – Grand Finale 2022
2022-11-28Machine learning for scientific discovery with examples in fluid mechanics | AI for Good Webinar
2022-11-27How to make AI more fair and unbiased | AI FOR GOOD DISCOVERY
2022-11-24AI for Good, or just better, cybersecurity | AI for Good Webinar
2022-11-23In AI we trust | AI for Good Webinar
2022-11-22Securing digital inclusion through AI | AI for Good Webinars
2022-11-21Towards human-centered social robots for good | AI for Good | Robotics for Good
2022-11-20Machine learning supporting ecology | AI for Good GeoAI Challenge
2022-11-17Project Resilience: Next steps for the Minimum Viable Product (MVP) | AI for Good Webinar
2022-11-16Multi Modal Beam Prediction Challenge 2022
2022-11-14Systematic deviations in data and model outputs in healthcare | AI for Good Discovery
2022-11-13Don’t Trust Your AI System: Model Its Validity Instead | Trustworthy AI | AI FOR GOOD
2022-11-09Meet the Robotics for Good start-ups advancing sustainable development | Robotics for Good