BROADCASTS.com

b'Today we\\u2019re excited to kick off our coverage of the 2022 NeurIPS conference with Johann Brehmer, a research scientist at Qualcomm AI Research in Amsterdam. We begin our conversation discussing some of the broader problems that causality will help us solve, before turning our focus to Johann\\u2019s 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\\u2019ll link to on the show notes page.\\xa0\\nThe complete show notes for this episode can be found at twimlai.com/go/605.'