video1.0<iframe src="https://www.loom.com/embed/446cdc07c87f470ea12755da8a661618" frameborder="0" width="1728" height="1296" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>12961728Loomhttps://www.loom.com12961728https://cdn.loom.com/sessions/thumbnails/446cdc07c87f470ea12755da8a661618-00001.gif1819Hi all, this is a mini-lecture recorded Apr 8, 2021 for Inter-Actief. The 'real' content starts at 1:34 and ends at about 28:46. The links and references on the slides: https://app.wooclap.com/ABIML/wall (to ask Doina questions whenever you get to this video) https://www.youtube.com/watch?v=Ok5sKLXqynQ “Are We Automating Racism?” (Vox), slide 4 https://science.sciencemag.org/content/366/6464/447 "Dissecting racial bias in an algorithm used to manage the health of populations", slides 7-9 https://arxiv.org/abs/2010.03058 "Characterising Bias in Compressed Models" (Google Research), slides 12-14 https://distill.pub/2021/multimodal-neurons/ "Multimodal Neurons in Artificial Neural Networks" (OpenAI), slides 15-16