Weakly Supervised Causal Representation Learning w/ Johann Brehmer

What are some of the broader problems that causality will help us over? We explore this and much more in our conversation with Johann Brehmer, a research scientist at Qualcomm AI Research in Amsterdam. In this first episode of our 2022 NeurIPS conference coverage, we focus on Johann’s paper Weakly supervised causal representation learning, which seeks to prove that high-level causal representations are identifiable in weakly supervised settings. We also discuss a few other papers that the team at Qualcomm presented, including neural topological ordering for computation graphs, as well as some of the demos they showcased, which we’ll link to on the show notes page. 🔔 Subscribe to our channel for more great content just like this: https://youtube.com/twimlai?sub_confi... 🗣️ CHAT WITH US! =============================== Subscribe to the TWIML AI Podcast: https://twimlai.com/podcast/twimlai/ Join our Slack Community: https://twimlai.com/community/ Subscribe to our newsletter: https://twimlai.com/newsletter/ Want to get in touch? Send us a message: https://twimlai.com/contact/ 🔗 LINKS & RESOURCES =============================== Blog: NeurIPS 2022: Qualcomm showcases cutting-edge advancements in machine learning - https://www.qualcomm.com/news/onq/202... Weakly supervised causal representation learning - https://arxiv.org/abs/2203.16437 Neural Topological Ordering for Computation Graphs - https://arxiv.org/abs/2207.05899 For access to the full list of resources from this episode, head over to https://twimlai.com/go/605. 📸 Camera: https://amzn.to/3TQ3zsg 🎙️Microphone: https://amzn.to/3t5zXeV 🚦Lights: https://amzn.to/3TQlX49 🎛️ Audio Interface: https://amzn.to/3TVFAIq 🎚️ Stream Deck: https://amzn.to/3zzm7F5