Dear all, Our next AI seminar on *"Building neural networks that know what they don’t know" *by Balaji Lakshminarayanan is scheduled to be on April 27th(Tomorrow), 1-2 PM PST (Add to google calendar <https://calendar.google.com/event?action=TEMPLATE&tmeid=YXExYTZuY2NiZXRhbHJ1MnBkdjAydTk1MmhfMjAyMjA0MjdUMjAwMDAwWiBjX25rNXRvdjk5bXZpZ2lnc3RndWEzcm11dGtzQGc&tmsrc=c_nk5tov99mvigigstgua3rmutks%40group.calendar.google.com> ). It will be followed by a 30-minute Q&A session by the graduate students. Zoom Link: https://oregonstate.zoom.us/j/93591935144?pwd=YjZaSjBYS0NmNUtjQzBEdzhPeDZ5UT... *Building neural networks that know what they don’t know* Balaji Lakshminarayanan Staff Research Scientist Google Brain *Abstract:* Deep neural networks can make overconfident errors and assign high confidence predictions to inputs far away from the training data. Well-calibrated predictive uncertainty estimates are important to know when to trust a model's predictions, especially for safe deployment of models in applications where the train and test distributions can be different. I'll first present some concrete examples that motivate the need for uncertainty and out-of-distribution (OOD) robustness in deep learning. Next, I'll present an overview of our recent work focused on building neural networks that know what they don’t know: this includes methods which improve single model uncertainty (e.g. spectral-normalized neural Gaussian processes), methods which average over multiple neural network predictions such as Bayesian neural nets and deep ensembles, and methods that leverage better representations (e.g. improving “near-OOD” detection). *Speaker Bio:* Balaji Lakshminarayanan is a staff research scientist at Google Brain. His recent research is focused on probabilistic deep learning, specifically, uncertainty estimation, out-of-distribution robustness and applications. Before joining Google Brain, he was a research scientist at DeepMind. He received his Ph.D. from the Gatsby Unit, University College London and Master’s degree from Oregon State University. He has co-organized several workshops on "Uncertainty and Robustness in deep learning" and served as Area Chair for NeurIPS, ICML, ICLR, and AISTATS. This talk will be followed by a talk on the topic "*Probabilistic Planning through the Lens of Approximate Inference*" by professor Roni Khardon on 4th May (Wednesday) 1-2 PM, 2022 *Please watch this space for future AI Seminars :* * https://eecs.oregonstate.edu/ai-events <https://eecs.oregonstate.edu/ai-events>* Rajesh Mangannavar, Graduate Student Oregon State University ---- AI Seminar Important Reminders: -> For graduate students in the AI program, attendance is strongly encouraged.